© 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. 9-LLAMASCOPE-RES-131K
    11. 94375
    Prev
    Next
    INDEX
    Explanations

    positive experiences and emotional engagement

    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
    dl
    -0.06
    .GetValue
    -0.06
    osi
    -0.06
    pv
    -0.06
     crypt
    -0.06
     Integral
    -0.06
    ewater
    -0.06
    ppard
    -0.06
    ãĥĥ
    -0.06
    ¼åIJĪ
    -0.06
    POSITIVE LOGITS
    _contrib
    0.07
    ERVED
    0.06
    iform
    0.06
    .Reporting
    0.06
     Humph
    0.06
    eç
    0.06
     Mour
    0.06
     Devil
    0.06
    irect
    0.06
     Ñģпад
    0.06
    Activations Density 0.117%

    No Known Activations