© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 27966
    Prev
    Next
    INDEX
    Explanations

    references to specific Apple products, particularly iPhones and iPads

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "iPhone" (and sometimes "iPad") in text, particularly in contexts related to apps, devices, and technology.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.19
    .scalablytyped
    -0.17
    itech
    -0.16
    ãģĤ
    -0.16
     Richardson
    -0.15
    uC
    -0.14
     Ideal
    -0.14
    owing
    -0.14
    agr
    -0.14
    nop
    -0.14
    POSITIVE LOGITS
    /i
    0.18
    /ip
    0.16
    audi
    0.15
    ology
    0.15
    /out
    0.15
     Ferd
    0.14
    léd
    0.14
    inally
    0.14
    pool
    0.14
    pell
    0.14
    Activations Density 0.005%

    No Known Activations