© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 79488
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols used in programming or scripting contexts

    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
    s
    -0.10
    m
    -0.07
    a
    -0.07
    i
    -0.07
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.07
    KANJI
    -0.07
    ERRQ
    -0.07
    eck
    -0.07
    *>(&
    -0.07
    n
    -0.07
    POSITIVE LOGITS
    0.06
    sole
    0.06
    urum
    0.06
    rador
    0.06
    -turned
    0.06
    /-
    0.06
     rever
    0.06
    atre
    0.06
    etal
    0.05
    vere
    0.05
    Activations Density 0.156%

    No Known Activations