© 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. 83104
    Prev
    Next
    INDEX
    Explanations

    equality or assignment operations in code

    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
    ptal
    -0.07
     ret
    -0.07
     mort
    -0.06
    rets
    -0.06
    ystore
    -0.06
     Mort
    -0.06
    ystal
    -0.05
    YN
    -0.05
    561
    -0.05
    ults
    -0.05
    POSITIVE LOGITS
    older
    0.08
    udem
    0.07
    etAddress
    0.07
    amu
    0.07
    ullo
    0.07
    /cpu
    0.07
    ุà¸Ĺ
    0.06
    449
    0.06
    oub
    0.06
    AM
    0.06
    Activations Density 0.000%

    No Known Activations