© 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. 17-LLAMASCOPE-RES-131K
    11. 79262
    Prev
    Next
    INDEX
    Explanations

    references to project specifications and contract details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIC
    -0.06
    vit
    -0.06
    Ãłu
    -0.06
     нанеÑģ
    -0.06
     ton
    -0.06
     coun
    -0.06
     bells
    -0.06
     psychology
    -0.06
     either
    -0.06
    ColumnType
    -0.06
    POSITIVE LOGITS
    003
    0.08
    001
    0.08
     Angiosper
    0.07
    202
    0.07
    lasses
    0.07
    002
    0.07
    020
    0.07
    _lng
    0.07
    201
    0.07
    ctors
    0.07
    Activations Density 0.046%

    No Known Activations