© 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 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. 118806
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols indicating structure in code

    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
    resse
    -0.07
     sond
    -0.07
    izont
    -0.07
    änn
    -0.07
    äll
    -0.07
    nave
    -0.07
    taire
    -0.07
     FetchType
    -0.06
    isode
    -0.06
    izon
    -0.06
    POSITIVE LOGITS
    UGH
    0.06
    iol
    0.06
    omers
    0.06
    in
    0.06
    Fact
    0.06
    fact
    0.06
    at
    0.06
    vol
    0.06
    _ASSUME
    0.06
    omer
    0.06
    Activations Density 0.004%

    No Known Activations