© 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. 71355
    Prev
    Next
    INDEX
    Explanations

    references to significant societal issues and concerns related to human rights

    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
    ï¼Ń
    -0.07
    šť
    -0.07
    ycz
    -0.07
    ÅĻe
    -0.07
    ÅĻiv
    -0.06
    çªģ
    -0.06
    iverz
    -0.06
    íķ
    -0.06
    à¸Ħว
    -0.06
    inux
    -0.06
    POSITIVE LOGITS
     Wolff
    0.06
    ights
    0.06
     Buckingham
    0.06
    olare
    0.06
    rade
    0.06
    rello
    0.06
     baseline
    0.06
     Wilkinson
    0.06
    idebar
    0.06
    kova
    0.05
    Activations Density 0.016%

    No Known Activations