© 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. 27645
    Prev
    Next
    INDEX
    Explanations

    mentions of references to media and notable events

    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
    asso
    -0.06
     ph
    -0.06
    ç¹
    -0.06
     breed
    -0.06
     Comics
    -0.06
    anse
    -0.06
    书
    -0.06
    CRYPT
    -0.05
     breeding
    -0.05
    auga
    -0.05
    POSITIVE LOGITS
     footage
    0.09
    cobra
    0.08
    otal
    0.07
    BorderStyle
    0.07
    /animate
    0.07
     vide
    0.07
    об
    0.07
     Shorts
    0.06
     clip
    0.06
     promo
    0.06
    Activations Density 0.002%

    No Known Activations