© 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. 15-LLAMASCOPE-RES-131K
    11. 90161
    Prev
    Next
    INDEX
    Explanations

    structural components and syntax in programming languages

    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
    #ad
    -0.08
    ignant
    -0.08
    yal
    -0.07
    Äł
    -0.07
    avn
    -0.07
    _scenario
    -0.07
    gett
    -0.07
     ↵↵
    -0.07
    loff
    -0.07
    StateException
    -0.07
    POSITIVE LOGITS
    ns
    0.06
     McM
    0.06
     Pil
    0.06
     typical
    0.06
     gez
    0.06
    imb
    0.06
    ome
    0.06
     Ride
    0.06
    ;
    0.06
     wash
    0.05
    Activations Density 0.001%

    No Known Activations