© 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. 107614
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating pauses or separations in text

    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
    hausen
    -0.07
    ott
    -0.06
    815
    -0.06
    omanip
    -0.06
    _revision
    -0.06
    _IT
    -0.06
    ateurs
    -0.05
     Deleted
    -0.05
    erek
    -0.05
    ERE
    -0.05
    POSITIVE LOGITS
    Äįka
    0.07
    rut
    0.07
    ag
    0.07
    intl
    0.07
    ÛĮتÛĮ
    0.07
    ange
    0.07
    ,,,
    0.06
    å¦
    0.06
    ñas
    0.06
    .lp
    0.06
    Activations Density 0.030%

    No Known Activations