© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106919
    Prev
    Next
    INDEX
    Explanations

    concerns related to social issues and community welfare

    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
    uhl
    -0.07
    //=
    -0.07
    rish
    -0.07
    ÅĻÃŃzenÃŃ
    -0.07
    quist
    -0.06
    AREST
    -0.06
    asmus
    -0.06
    istrovstvÃŃ
    -0.06
     Hamm
    -0.06
    loo
    -0.06
    POSITIVE LOGITS
    lyph
    0.08
    riet
    0.07
    spm
    0.07
    erb
    0.06
    fen
    0.06
    зд
    0.06
    FormItem
    0.06
    ped
    0.06
    åķ
    0.06
    åĭ
    0.06
    Activations Density 0.002%

    No Known Activations