© 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. 92184
    Prev
    Next
    INDEX
    Explanations

    names of locations and events in relation to performances or gatherings

    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
    agua
    -0.06
    ami
    -0.06
     AND
    -0.06
    ,
    -0.06
    ÙĪÛĮÙĩ
    -0.06
     alone
    -0.06
    emi
    -0.06
    :
    -0.05
    cala
    -0.05
     Campos
    -0.05
    POSITIVE LOGITS
     Äijá»ĥ
    0.09
     ÑĩÑĤобÑĭ
    0.09
     tonight
    0.08
    为äºĨ
    0.08
    today
    0.07
     today
    0.07
     Ñīоб
    0.07
     afin
    0.07
     yesterday
    0.07
     aby
    0.07
    Activations Density 0.030%

    No Known Activations