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. 22-LLAMASCOPE-RES-131K
    6. 5610
    Prev
    Next
    INDEX
    Explanations

    date references in a document

    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
    atcher
    -0.06
    ÑĪка
    -0.06
     Morg
    -0.06
     UserData
    -0.06
    onde
    -0.06
    osate
    -0.06
    assis
    -0.06
    lotte
    -0.06
    antee
    -0.06
    irá
    -0.05
    POSITIVE LOGITS
    å¥Ī
    0.08
    unfinished
    0.06
     ï¿¥
    0.06
    isci
    0.06
    è¡
    0.06
     Rev
    0.06
    984
    0.06
    uyu
    0.06
    ìļ¸
    0.06
    *****/↵
    0.06
    Activations Density 0.009%

    No Known Activations