© 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. 108236
    Prev
    Next
    INDEX
    Explanations

    keywords associated with organizational roles and activities

    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
    Ā
    -0.08
     -*-č↵
    -0.08
    .':
    -0.08
    .lex
    -0.07
    Ùį
    -0.07
    ÑĪа
    -0.07
    lerce
    -0.07
     Quy
    -0.07
    ampton
    -0.07
    ÑĽ
    -0.07
    POSITIVE LOGITS
    ÙĪاء
    0.07
    CCCCCC
    0.07
    _HERSHEY
    0.07
    -extra
    0.06
    ERSHEY
    0.06
    IntegerField
    0.06
    ULLET
    0.06
    gamber
    0.06
    ÑĤеÑĢн
    0.06
    TECTED
    0.06
    Activations Density 0.057%

    No Known Activations