© 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. 94832
    Prev
    Next
    INDEX
    Explanations

    references to specific measurements, identifiers, or numerical data

    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
    ModelIndex
    -0.07
    çı
    -0.07
     Beste
    -0.07
    егоÑĢ
    -0.07
    ictim
    -0.07
    ogy
    -0.07
     addCriterion
    -0.07
    aný
    -0.07
    anje
    -0.07
    å·ŀå¸Ĥ
    -0.07
    POSITIVE LOGITS
    ëŀ¨
    0.06
    bot
    0.06
     Fare
    0.06
    .TODO
    0.06
    utt
    0.06
    apt
    0.05
    ANCE
    0.05
    au
    0.05
     met
    0.05
     same
    0.05
    Activations Density 0.001%

    No Known Activations