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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76509
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically periods

    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
     somew
    -0.06
     Micro
    -0.06
     Bar
    -0.06
    esco
    -0.06
    swer
    -0.06
    unker
    -0.06
    ESCO
    -0.06
    .micro
    -0.06
    jk
    -0.06
    hoot
    -0.06
    POSITIVE LOGITS
    borg
    0.07
     ÑĪи
    0.06
    æĨ
    0.06
    ç´
    0.06
     eins
    0.06
    disposing
    0.06
    loth
    0.06
     SqlParameter
    0.06
    ̣
    0.06
    åĭ¢
    0.06
    Activations Density 0.000%

    No Known Activations