© 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. 84507
    Prev
    Next
    INDEX
    Explanations

    conditional statements and scenarios

    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
    auga
    -0.07
    %X
    -0.07
     McG
    -0.07
    uplic
    -0.06
    /portfolio
    -0.06
    [url
    -0.06
    ĥ
    -0.06
    GED
    -0.06
     headache
    -0.06
    oise
    -0.05
    POSITIVE LOGITS
    æĪij
    0.09
    372
    0.07
     tôi
    0.07
    olian
    0.07
    ervo
    0.07
    pez
    0.07
    ami
    0.07
     saya
    0.07
    ano
    0.06
    gnore
    0.06
    Activations Density 0.015%

    No Known Activations