© 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. 16686
    Prev
    Next
    INDEX
    Explanations

    specific locations or addresses mentioned 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
     downtown
    -0.07
    uelle
    -0.07
     Downtown
    -0.07
     Alley
    -0.07
     Primitive
    -0.07
    wert
    -0.07
     Bureau
    -0.06
     alley
    -0.06
    gratis
    -0.06
    umpt
    -0.06
    POSITIVE LOGITS
     suburban
    0.09
     suburb
    0.08
     Golf
    0.07
     Brom
    0.07
    ascal
    0.07
     Wimbledon
    0.07
     경기ëıĦ
    0.07
    trace
    0.07
     PT
    0.06
     affluent
    0.06
    Activations Density 0.256%

    No Known Activations