Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96121
    Prev
    Next
    INDEX
    Explanations

    genres and categories related to film and television

    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
    geries
    -0.07
     I
    -0.06
     til
    -0.06
     credits
    -0.06
     unw
    -0.06
     Pessoa
    -0.05
    aveled
    -0.05
     credit
    -0.05
     Pere
    -0.05
    608
    -0.05
    POSITIVE LOGITS
    Äįan
    0.07
    λεκ
    0.07
     ObjectType
    0.07
    ména
    0.07
    LookAndFeel
    0.07
    _INCLUDED
    0.07
    .cx
    0.07
    ãģĭãģij
    0.06
     ðŁĶ
    0.06
     navr
    0.06
    Activations Density 0.003%

    No Known Activations