© 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. 120165
    Prev
    Next
    INDEX
    Explanations

    references to technological concepts and tools related to engineering and programming

    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
    087
    -0.06
     Tat
    -0.06
    amel
    -0.06
    ometr
    -0.06
    -To
    -0.06
     Hess
    -0.06
    -to
    -0.06
     sant
    -0.06
    OI
    -0.06
    arl
    -0.06
    POSITIVE LOGITS
     ÑĩÑĤобÑĭ
    0.10
     to
    0.10
     Äijá»ĥ
    0.10
     Ñīоб
    0.08
     να
    0.08
     kullanarak
    0.07
    ingleton
    0.07
    .jdesktop
    0.07
    vÄĽÅĻ
    0.07
    -gnu
    0.07
    Activations Density 0.040%

    No Known Activations