© 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. 57549
    Prev
    Next
    INDEX
    Explanations

    programming-related test structures and functions

    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
    Ùĥت
    -0.06
    lev
    -0.06
    ardy
    -0.06
     ëĦ¤ìĿ´íĬ¸
    -0.06
    -CP
    -0.06
    Ģ
    -0.06
    ToShow
    -0.06
    atta
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    rdf
    -0.06
    POSITIVE LOGITS
    ieux
    0.08
     misc
    0.08
    buah
    0.06
    &apos
    0.06
    cret
    0.06
    ibold
    0.06
    amt
    0.06
    asca
    0.06
    harga
    0.06
    _misc
    0.06
    Activations Density 0.007%

    No Known Activations