© 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 EvalsExportsAPI 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. 130972
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or groups in various contexts

    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
    razy
    -0.06
    uso
    -0.06
    veau
    -0.06
    ald
    -0.06
    atives
    -0.06
     needles
    -0.06
    ega
    -0.06
    akter
    -0.06
    ONGL
    -0.06
    ạn
    -0.06
    POSITIVE LOGITS
     nÃło
    0.09
    calar
    0.08
     portions
    0.08
    /all
    0.08
     parts
    0.07
     persons
    0.07
     who
    0.07
     individuals
    0.07
    YM
    0.07
    EDI
    0.07
    Activations Density 0.025%

    No Known Activations