© 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. 71279
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or sentence-ending symbols

    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
    lements
    -0.07
    achu
    -0.07
     Mare
    -0.06
    yro
    -0.06
    ckt
    -0.06
    buat
    -0.06
    азв
    -0.06
     pits
    -0.06
    ÙĬÙĦØ©
    -0.06
    leta
    -0.06
    POSITIVE LOGITS
     interviewer
    0.07
    239
    0.07
    EMS
    0.06
     interview
    0.06
     Interview
    0.06
     entrev
    0.06
     transcript
    0.06
    .timestamps
    0.06
    Interview
    0.06
    访
    0.06
    Activations Density 0.000%

    No Known Activations