© 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. 16599
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or references to chemical compounds

    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
    ritz
    -0.07
    Interpolator
    -0.07
    ãĥ¼ãĥĬ
    -0.06
     suiv
    -0.06
    ê´Ģ
    -0.06
    ropp
    -0.06
    egan
    -0.06
    rů
    -0.06
    mlin
    -0.06
    Dice
    -0.06
    POSITIVE LOGITS
    ycin
    0.07
    ierge
    0.06
    лÑĥж
    0.06
    frey
    0.06
     Benson
    0.06
    รà¸Ķ
    0.06
     Editors
    0.06
    _GRANTED
    0.06
     Laurel
    0.06
    skin
    0.06
    Activations Density 0.000%

    No Known Activations