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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 57408
    Prev
    Next
    INDEX
    Explanations

    references to social and political activism

    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
    รà¸ĩ
    -0.08
    磨
    -0.08
    )new
    -0.08
    ÏĩεδÏĮν
    -0.08
    eza
    -0.07
    виÑħ
    -0.07
    asks
    -0.07
    ίθ
    -0.07
    .BLL
    -0.07
    ãİ
    -0.07
    POSITIVE LOGITS
     Bout
    0.07
     former
    0.07
     self
    0.07
    itted
    0.06
     who
    0.06
     serial
    0.06
     auto
    0.06
    mr
    0.06
     disabled
    0.06
    imar
    0.06
    Activations Density 0.021%

    No Known Activations