© 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. 59402
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
     Dahl
    -0.06
    oba
    -0.06
    боÑĤ
    -0.06
    iox
    -0.06
    ako
    -0.06
    WithTag
    -0.06
    à¹Īà¸Ńย
    -0.06
    æ°ı
    -0.06
    å±±å¸Ĥ
    -0.06
     komment
    -0.06
    POSITIVE LOGITS
    AZY
    0.07
    uvw
    0.07
    bos
    0.07
    redits
    0.07
    vig
    0.06
    EOS
    0.06
    CJK
    0.06
    产
    0.06
    rames
    0.06
    mes
    0.06
    Activations Density 0.019%

    No Known Activations