© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 120022
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods and brackets

    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
     addCriterion
    -0.07
    ãĥĨãĥ«
    -0.07
    ante
    -0.07
    olumn
    -0.07
    @brief
    -0.07
    ruba
    -0.07
    úi
    -0.07
    ancell
    -0.07
    atak
    -0.06
    ãĤ
    -0.06
    POSITIVE LOGITS
    بØŃ
    0.07
    _stub
    0.06
     пÑĢеÑģ
    0.06
     vér
    0.06
    ijo
    0.05
    bjerg
    0.05
     Zug
    0.05
    wick
    0.05
    .MSG
    0.05
     eens
    0.05
    Activations Density 0.008%

    No Known Activations