© 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. 119472
    Prev
    Next
    INDEX
    Explanations

    the string "eci."

    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
    agnostics
    -0.08
    chg
    -0.07
    zl
    -0.07
    idor
    -0.07
    è¡Ĩ
    -0.07
    ÑĢава
    -0.07
    kud
    -0.07
    jde
    -0.06
     PureComponent
    -0.06
    odash
    -0.06
    POSITIVE LOGITS
    dsn
    0.07
    emes
    0.06
    jee
    0.06
     Entire
    0.06
    å£ģ
    0.06
    ajes
    0.06
     whenever
    0.06
     entire
    0.06
    uyá»ĩt
    0.05
     nich
    0.05
    Activations Density 0.000%

    No Known Activations