© 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. 92019
    Prev
    Next
    INDEX
    Explanations

    terms related to account management and community engagement

    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
    ÂŃ
    -0.07
    âĢ¦↵
    -0.07
    aug
    -0.06
     of
    -0.06
     [âĢ¦]↵
    -0.06
    _HERSHEY
    -0.05
    enger
    -0.05
    -0.05
    [email
    -0.05
     âĢ¦↵
    -0.05
    POSITIVE LOGITS
     lô
    0.10
     .|
    0.10
    .Îł
    0.08
     зави
    0.08
    PDO
    0.08
    erli
    0.08
    _AI
    0.08
     poil
    0.08
    .↵↵↵↵↵↵↵↵
    0.08
     обÑĢа
    0.08
    Activations Density 0.036%

    No Known Activations