© 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. 42144
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "do" in different contexts

    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
    IFI
    -0.08
    SSI
    -0.07
    utter
    -0.07
     dri
    -0.07
    448
    -0.07
    dra
    -0.06
    /XMLSchema
    -0.06
    лий
    -0.06
    å¸Ŀ
    -0.06
    unk
    -0.06
    POSITIVE LOGITS
    zens
    0.07
    RAP
    0.07
    pez
    0.06
    aria
    0.06
    ville
    0.06
    ç¬Ķ
    0.06
    bbe
    0.06
    à¹ĩà¸Ļà¸ŀ
    0.06
    ÃĹ↵↵
    0.06
    ãİ¡
    0.06
    Activations Density 0.025%

    No Known Activations