© 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. 126322
    Prev
    Next
    INDEX
    Explanations

    code structures and programming constructs

    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
    oxy
    -0.07
    Ñĸ
    -0.06
    親
    -0.06
    hea
    -0.06
    oun
    -0.06
    ain
    -0.05
     Picks
    -0.05
    loor
    -0.05
    J
    -0.05
     immunity
    -0.05
    POSITIVE LOGITS
     rosa
    0.07
    iki
    0.07
    >NN
    0.07
     private
    0.07
     public
    0.06
    оÑĢож
    0.06
    },{↵
    0.06
    walker
    0.06
    era
    0.06
     onViewCreated
    0.06
    Activations Density 0.018%

    No Known Activations