© 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. 56283
    Prev
    Next
    INDEX
    Explanations

    documentation comments in code

    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
    ses
    -0.07
    ucks
    -0.07
    ti
    -0.07
    hr
    -0.07
    halb
    -0.07
    mar
    -0.06
    ci
    -0.06
    house
    -0.06
    VOKE
    -0.06
     Liberties
    -0.06
    POSITIVE LOGITS
    spl
    0.07
    Lens
    0.07
     @}
    0.07
    forth
    0.07
    	↵
    0.07
    wij
    0.07
    apons
    0.06
    icana
    0.06
    perimental
    0.06
    fully
    0.06
    Activations Density 0.004%

    No Known Activations