© 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. 15-LLAMASCOPE-RES-131K
    11. 103867
    Prev
    Next
    INDEX
    Explanations

    references to gang-related dynamics and their interaction with politics and community issues

    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
    iero
    -0.07
    uru
    -0.07
    contenido
    -0.07
    licht
    -0.06
    å¥ij
    -0.06
    ackle
    -0.06
    .override
    -0.06
    æķ·
    -0.06
    ATH
    -0.06
    chantment
    -0.06
    POSITIVE LOGITS
    idual
    0.07
    /drivers
    0.07
    Alias
    0.07
    /groups
    0.07
    opro
    0.07
    åħĭæĸ¯
    0.06
    eyin
    0.06
     IDM
    0.06
    /docs
    0.06
    鼨
    0.06
    Activations Density 0.002%

    No Known Activations