© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87670
    Prev
    Next
    INDEX
    Explanations

    specific data types and structure in programming code

    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
     laps
    -0.07
    ayment
    -0.06
    licken
    -0.06
    ushing
    -0.06
    alist
    -0.06
     Sole
    -0.06
    illance
    -0.06
    lee
    -0.06
    ledon
    -0.06
     Owl
    -0.06
    POSITIVE LOGITS
    gro
    0.06
    gons
    0.06
     pepper
    0.06
    EMALE
    0.06
     break
    0.06
    upo
    0.06
    break
    0.06
     Streets
    0.06
    pur
    0.06
    ampo
    0.06
    Activations Density 0.047%

    No Known Activations