© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82797
    Prev
    Next
    INDEX
    Explanations

    punctuation at the end of sentences and clauses

    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
    imson
    -0.07
     Pearce
    -0.07
     ambit
    -0.06
    lick
    -0.06
    015
    -0.06
    655
    -0.06
     cess
    -0.06
     cult
    -0.06
    KN
    -0.06
    ino
    -0.05
    POSITIVE LOGITS
    .twitch
    0.08
    گز
    0.07
    _PT
    0.07
    ESIS
    0.07
    _SKIP
    0.07
    à¸Ńว
    0.07
     ----------------------------------------------------------------------↵
    0.07
    Úĺ
    0.07
    è«
    0.07
    dit
    0.06
    Activations Density 0.015%

    No Known Activations