© 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. 87166
    Prev
    Next
    INDEX
    Explanations

    themes related to societal prejudice and fear

    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
    uing
    -0.07
    iek
    -0.07
     Lambda
    -0.06
    /org
    -0.06
    ajas
    -0.06
    uin
    -0.06
     Guerr
    -0.06
    ansk
    -0.06
    punk
    -0.06
    lasses
    -0.06
    POSITIVE LOGITS
     profiling
    0.07
     stere
    0.07
     incumb
    0.07
     discrimination
    0.07
     rám
    0.07
     altura
    0.07
    _CBC
    0.07
    кÑĢаÑĹ
    0.07
     Dost
    0.07
     Exped
    0.06
    Activations Density 0.004%

    No Known Activations