© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77050
    Prev
    Next
    INDEX
    Explanations

    interactions and responses during customer service situations

    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
    _:*
    -0.07
    BITS
    -0.07
    uml
    -0.07
    anse
    -0.06
    ainen
    -0.06
    ODB
    -0.06
    íĻ©
    -0.06
    RD
    -0.06
    ongyang
    -0.06
     hopefully
    -0.06
    POSITIVE LOGITS
     Leisure
    0.07
    plx
    0.07
     basically
    0.07
     literally
    0.06
    ôi
    0.06
    iegel
    0.06
     Observable
    0.06
    oyal
    0.06
     ves
    0.06
    uu
    0.06
    Activations Density 0.016%

    No Known Activations