© 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. 108351
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and structures related to OAuth and server management

    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
    ether
    -0.07
    ezi
    -0.07
     Stones
    -0.06
     Harvey
    -0.06
    ÑĢоÑĩ
    -0.06
    sein
    -0.06
    yo
    -0.06
    Enter
    -0.06
     Fell
    -0.06
    arsi
    -0.06
    POSITIVE LOGITS
     urn
    0.08
     Social
    0.07
    社
    0.07
    ÏĦον
    0.07
    eldorf
    0.07
    Łèĥ½
    0.07
    ?q
    0.06
    _challenge
    0.06
     social
    0.06
    eldon
    0.06
    Activations Density 0.009%

    No Known Activations