© 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. 82925
    Prev
    Next
    INDEX
    Explanations

    references to titles, authors, or publishing details in texts

    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
    agua
    -0.08
     Italy
    -0.07
    achu
    -0.07
    azo
    -0.07
    alink
    -0.07
    ASURE
    -0.07
    ereotype
    -0.07
    liga
    -0.07
    ITAL
    -0.07
    /repos
    -0.07
    POSITIVE LOGITS
    ò
    0.09
    ì
    0.08
    è
    0.07
     Rover
    0.07
    TL
    0.07
    زÙĩ
    0.06
    òn
    0.06
     finanzi
    0.06
     giÃł
    0.06
     Nic
    0.06
    Activations Density 0.070%

    No Known Activations