© 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. 3309
    Prev
    Next
    INDEX
    Explanations

    specific names of universities and related institutions

    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
    äh
    -0.08
    Äĥ
    -0.07
    çģ½
    -0.06
    кÑĥÑĤ
    -0.06
    raman
    -0.06
     Kak
    -0.06
    ESIS
    -0.06
    ailable
    -0.06
    orry
    -0.06
    inox
    -0.06
    POSITIVE LOGITS
    _handlers
    0.07
    ensi
    0.06
    vu
    0.06
    rese
    0.06
    _notifications
    0.06
     region
    0.06
    unce
    0.06
    ãģĵ
    0.06
    fu
    0.06
    itore
    0.06
    Activations Density 0.016%

    No Known Activations