© 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. 18204
    Prev
    Next
    INDEX
    Explanations

    mentions of entities related to government or authority

    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
     çĬ
    -0.07
    ове
    -0.07
    upal
    -0.07
    agem
    -0.07
    asio
    -0.07
    eller
    -0.06
    reich
    -0.06
    Äĵ
    -0.06
    leon
    -0.06
    ingham
    -0.06
    POSITIVE LOGITS
    oble
    0.07
    ritel
    0.07
    nier
    0.06
     Fauc
    0.06
    omo
    0.06
     valueForKey
    0.06
    imson
    0.06
     coll
    0.05
    ÑĪиÑģÑĮ
    0.05
    benh
    0.05
    Activations Density 0.001%

    No Known Activations