© 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. 119545
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in the text

    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
    ìĿµ
    -0.08
    itel
    -0.08
    ãĤ·ãĤ¢
    -0.08
    rale
    -0.07
    dden
    -0.07
    eras
    -0.07
     ìĿµ
    -0.07
     तर
    -0.07
    heimer
    -0.07
    Å¡tÄĽ
    -0.07
    POSITIVE LOGITS
    adem
    0.07
     tomorrow
    0.07
     speaking
    0.07
     spoke
    0.06
     speak
    0.06
     Attendance
    0.06
    ätt
    0.06
    ãĢģä»Ĭ
    0.06
    quotes
    0.06
     speaks
    0.06
    Activations Density 0.008%

    No Known Activations