Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5345
    Prev
    Next
    INDEX
    Explanations

    words related to professions and titles

    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
     addCriterion
    -0.08
    vs
    -0.08
    fav
    -0.07
    PixelFormat
    -0.07
    ieu
    -0.07
    /frontend
    -0.07
    eil
    -0.07
    czy
    -0.07
    rende
    -0.07
    loquent
    -0.07
    POSITIVE LOGITS
     wherever
    0.07
    305
    0.06
    *)_
    0.05
    788
    0.05
    outer
    0.05
    िण
    0.05
    ,
    0.05
     Blue
    0.05
    orado
    0.05
     distant
    0.05
    Activations Density 0.002%

    No Known Activations