© 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. 29537
    Prev
    Next
    INDEX
    Explanations

    references to communities or groups

    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
     Kai
    -0.06
     >",
    -0.06
     laps
    -0.06
    oned
    -0.05
    Äı
    -0.05
    ç©į
    -0.05
    469
    -0.05
    /live
    -0.05
     pieces
    -0.05
     fri
    -0.05
    POSITIVE LOGITS
     list
    0.09
    list
    0.09
    ë³Ħ
    0.08
     Evel
    0.08
    cano
    0.08
    stable
    0.07
    ame
    0.07
    ëĿ½
    0.07
    sto
    0.07
    namen
    0.07
    Activations Density 0.045%

    No Known Activations