© 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. 87712
    Prev
    Next
    INDEX
    Explanations

    references to software or package versions being outdated

    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
    leh
    -0.08
    inia
    -0.07
    ittal
    -0.07
    ichel
    -0.07
    λÎŃ
    -0.07
    elig
    -0.07
    baugh
    -0.07
    à¸Ľà¸£à¸°à¸Īำ
    -0.07
    orf
    -0.06
    ionales
    -0.06
    POSITIVE LOGITS
     maintain
    0.09
     maint
    0.08
     maintained
    0.08
     development
    0.08
     code
    0.07
     Maint
    0.07
     mant
    0.07
     maintenance
    0.07
    ç»´
    0.07
     Development
    0.07
    Activations Density 0.008%

    No Known Activations