© 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. 123822
    Prev
    Next
    INDEX
    Explanations

    questions related to personal experiences and advice

    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
    çĽĸ
    -0.07
    pra
    -0.07
    idual
    -0.06
     Ain
    -0.06
    ायद
    -0.06
    iddet
    -0.06
    many
    -0.06
    sg
    -0.06
    sher
    -0.06
    primer
    -0.06
    POSITIVE LOGITS
    ?↵
    0.07
    ï¼Ł↵
    0.07
     EITHER
    0.06
    iglia
    0.06
    ooks
    0.06
     either
    0.06
     Describe
    0.06
    ETS
    0.06
    _singular
    0.06
    ãģ§ãģĻãģĭ
    0.06
    Activations Density 0.019%

    No Known Activations