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

    Neuronpedia

    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. 21518
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presence and understanding of necessary resources or skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    asti
    -0.16
    isel
    -0.16
    groupid
    -0.16
     Viol
    -0.16
     Hodg
    -0.15
    acos
    -0.15
     boj
    -0.15
    gesi
    -0.14
    teki
    -0.14
    orno
    -0.14
    POSITIVE LOGITS
     necessary
    0.15
     flushed
    0.14
    lux
    0.14
     Donovan
    0.14
    AEA
    0.13
    ABI
    0.13
     authority
    0.13
     THR
    0.13
    inator
    0.13
    pher
    0.13
    Activations Density 0.048%

    No Known Activations