© 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. 71162
    Prev
    Next
    INDEX
    Explanations

    references to public health policies and their implications

    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
    Å¡ÃŃm
    -0.07
    strup
    -0.07
    erule
    -0.07
    ÏĥÏĦαν
    -0.07
    cola
    -0.07
    allo
    -0.06
    foreground
    -0.06
    mpp
    -0.06
    Å¡ÃŃch
    -0.06
    gcd
    -0.06
    POSITIVE LOGITS
    uh
    0.06
     Miles
    0.06
     reserved
    0.06
    ammers
    0.06
    :↵
    0.06
     conven
    0.06
     MCP
    0.06
    uci
    0.06
    :↵↵
    0.05
    isure
    0.05
    Activations Density 0.000%

    No Known Activations