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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 43462
    Prev
    Next
    INDEX
    Explanations

    special characters or unicode symbols

    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
    ospel
    -0.06
    祥
    -0.06
    aleigh
    -0.06
     tolua
    -0.05
    èĤ²
    -0.05
    avras
    -0.05
    å¹³
    -0.05
    /script
    -0.05
    ildo
    -0.05
    êm
    -0.05
    POSITIVE LOGITS
     Psych
    0.16
    Psych
    0.15
     behavioral
    0.15
     psych
    0.15
     psychologists
    0.15
    psych
    0.14
     psychology
    0.14
     Psychology
    0.14
     psychologist
    0.14
     Behavioral
    0.14
    Activations Density 0.003%

    No Known Activations