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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60256
    Prev
    Next
    INDEX
    Explanations

    occurrences of quotation marks and related punctuation

    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
    ilden
    -0.07
    boom
    -0.07
    lude
    -0.07
    riba
    -0.06
    orte
    -0.06
    stell
    -0.06
    -wrap
    -0.06
    atty
    -0.06
     BITS
    -0.06
    upal
    -0.06
    POSITIVE LOGITS
    iska
    0.07
     eskort
    0.07
    ÂĢÂ
    0.06
    aker
    0.06
    "class
    0.06
    Äĥm
    0.06
    asurer
    0.06
    .tp
    0.06
    .mj
    0.06
     Wid
    0.06
    Activations Density 0.018%

    No Known Activations