© 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. 61327
    Prev
    Next
    INDEX
    Explanations

    references to academic or journal articles

    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
    aron
    -0.07
     CircularProgress
    -0.07
    лиÑĤ
    -0.07
    arge
    -0.06
    alie
    -0.06
    conscious
    -0.06
    ardu
    -0.06
    ấm
    -0.06
    okie
    -0.06
    primaryKey
    -0.06
    POSITIVE LOGITS
    ÐIJÑĢÑħÑĸвовано
    0.12
    +]
    0.07
    !]
    0.07
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    0.07
    sic
    0.07
    ?]
    0.07
    ARIANT
    0.07
    åľ¨çº¿éĺħ读
    0.07
    .]↵↵
    0.07
    Ïģκ
    0.07
    Activations Density 0.037%

    No Known Activations