© 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. 12390
    Prev
    Next
    INDEX
    Explanations

    instances of the word "had"

    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
    uchs
    -0.16
    ussen
    -0.16
    able
    -0.16
    vál
    -0.15
    eries
    -0.15
    едÑĮ
    -0.15
    éĢ¸
    -0.14
    DDL
    -0.14
    VENT
    -0.13
    abis
    -0.13
    POSITIVE LOGITS
     originally
    0.21
     previously
    0.20
     earlier
    0.20
     hoped
    0.19
    nt
    0.17
     formerly
    0.16
     سابÙĤ
    0.16
    ont
    0.16
     Previously
    0.15
     Earlier
    0.15
    Activations Density 0.164%

    No Known Activations