© 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. 95411
    Prev
    Next
    INDEX
    Explanations

    references to political entities and structures, particularly in an Italian context

    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
    _Params
    -0.06
     bin
    -0.06
     SOLD
    -0.06
    .setPrototypeOf
    -0.05
    Âł
    -0.05
    важ
    -0.05
     Obs
    -0.05
     Bin
    -0.05
     “
    -0.05
     util
    -0.05
    POSITIVE LOGITS
    eless
    0.08
    reesome
    0.07
    ibold
    0.07
    loff
    0.07
    ked
    0.07
    lew
    0.07
    antee
    0.07
     пеÑĢи
    0.07
    ragen
    0.07
    raquo
    0.07
    Activations Density 0.006%

    No Known Activations