© 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. 118626
    Prev
    Next
    INDEX
    Explanations

    Unicode and special character sequences

    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
    annes
    -0.09
    hta
    -0.07
    ÃĹ↵↵
    -0.07
    ayo
    -0.07
    .bz
    -0.07
    255
    -0.07
    imoto
    -0.07
    илÑı
    -0.07
    Ļ¨
    -0.07
    ropri
    -0.07
    POSITIVE LOGITS
    orie
    0.07
    롱
    0.06
    ĭ
    0.06
    /native
    0.06
    ced
    0.06
    .localization
    0.06
    lys
    0.06
    à¥Ĥस
    0.06
    ãģĤãģ£ãģŁ
    0.06
     weather
    0.06
    Activations Density 0.003%

    No Known Activations