© 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. 55977
    Prev
    Next
    INDEX
    Explanations

    code structures, particularly around function definitions and conditional statements

    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
     cross
    -0.07
     inv
    -0.06
    synthesize
    -0.06
    265
    -0.05
    ãģĵãģ¡ãĤī
    -0.05
    sic
    -0.05
     NOTES
    -0.05
    aben
    -0.05
    getQuery
    -0.05
     “
    -0.05
    POSITIVE LOGITS
    oks
    0.08
    imuth
    0.07
    kah
    0.07
     dále
    0.07
    ildren
    0.07
    å·Ŀ
    0.07
    deaux
    0.07
    dit
    0.07
    iá»ĥu
    0.07
    гл
    0.07
    Activations Density 0.104%

    No Known Activations