© 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. 92246
    Prev
    Next
    INDEX
    Explanations

    terms related to searching for or locating something

    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
    _defs
    -0.08
    ολ
    -0.08
    iqueta
    -0.08
    regar
    -0.08
    ji
    -0.08
    plings
    -0.07
    .RunWith
    -0.07
     Ø®ÙĪ
    -0.07
    zych
    -0.07
    adium
    -0.07
    POSITIVE LOGITS
     whereabouts
    0.08
     missing
    0.08
     lost
    0.07
     answers
    0.07
     elusive
    0.07
     Answers
    0.07
    791
    0.07
     Missing
    0.06
     sought
    0.06
     evidence
    0.06
    Activations Density 0.016%

    No Known Activations