© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 14210
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data handling within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grove
    -0.14
     Duffy
    -0.14
    argo
    -0.13
    .RightToLeft
    -0.13
    poons
    -0.13
    ãģ¬
    -0.12
    äs
    -0.12
    upy
    -0.11
    _simps
    -0.11
    ataire
    -0.11
    POSITIVE LOGITS
     Gen
    1.02
     gen
    1.00
    Gen
    0.96
    gen
    0.96
     generation
    0.96
    -gen
    0.95
     GEN
    0.93
     Gener
    0.93
     Generation
    0.92
     generator
    0.91
    Activations Density 0.401%

    No Known Activations