© 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. 4780
    Prev
    Next
    INDEX
    Explanations

    phrases expressing opinions or sentiments about books

    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
     Niet
    -0.07
    ette
    -0.06
    hani
    -0.06
     Jaime
    -0.06
    ãĢ
    -0.06
    444
    -0.06
     Villa
    -0.06
     danh
    -0.06
    GetName
    -0.06
    oley
    -0.05
    POSITIVE LOGITS
    od
    0.07
    kk
    0.07
    odo
    0.07
    udu
    0.06
     defaultMessage
    0.06
    oder
    0.06
    idas
    0.06
    Äįin
    0.06
    ZR
    0.06
    ucky
    0.06
    Activations Density 0.000%

    No Known Activations