© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77072
    Prev
    Next
    INDEX
    Explanations

    references to corporate governance and organizational structure

    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
    antz
    -0.07
    loff
    -0.07
    minster
    -0.07
    affer
    -0.07
    ccoli
    -0.07
    Ľ°
    -0.07
    chine
    -0.07
    ailability
    -0.06
    readcr
    -0.06
    alte
    -0.06
    POSITIVE LOGITS
     Ñħол
    0.07
    WithType
    0.06
     boarded
    0.06
     Odd
    0.06
    пÑĢ
    0.06
     ØŃص
    0.06
     Voting
    0.06
     Vega
    0.06
    uder
    0.06
    ivy
    0.06
    Activations Density 0.004%

    No Known Activations