© 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. 105267
    Prev
    Next
    INDEX
    Explanations

    references to the field of molecular sciences and related disciplines

    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
    TING
    -0.08
    sert
    -0.07
    tings
    -0.07
     voks
    -0.07
    desk
    -0.07
    gh
    -0.07
     Bale
    -0.07
    Fcn
    -0.07
    inn
    -0.06
    ÅĻaz
    -0.06
    POSITIVE LOGITS
    ly
    0.08
    neau
    0.07
     Blonde
    0.07
    ized
    0.06
     medicine
    0.06
    -level
    0.06
    aison
    0.06
    -scale
    0.06
    aight
    0.06
    zÄĻ
    0.06
    Activations Density 0.007%

    No Known Activations