© 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. 106970
    Prev
    Next
    INDEX
    Explanations

    semicolons used in code, likely indicating the structure of programming statements

    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
    coder
    -0.07
    ë³Ħ
    -0.06
     Wikip
    -0.06
    êµIJ
    -0.06
    çu
    -0.06
     kino
    -0.06
    cÃŃ
    -0.06
    vál
    -0.06
     centerX
    -0.06
    ĵåIJį
    -0.05
    POSITIVE LOGITS
    935
    0.08
    ToLocal
    0.07
    nev
    0.07
    apest
    0.07
     Tun
    0.07
    osal
    0.06
    addon
    0.06
    ninger
    0.06
    emouth
    0.06
    retval
    0.06
    Activations Density 0.001%

    No Known Activations