© 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. 79297
    Prev
    Next
    INDEX
    Explanations

    instances of group participation or collaboration

    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
    orgia
    -0.07
    ¤í
    -0.07
    £½
    -0.07
     nackte
    -0.07
    opoulos
    -0.07
    antas
    -0.06
    oger
    -0.06
    irsch
    -0.06
    kits
    -0.06
    ikut
    -0.06
    POSITIVE LOGITS
    οÏģ
    0.07
    UME
    0.07
    vä
    0.07
    ume
    0.07
    (disposing
    0.06
    vise
    0.06
     Bender
    0.06
    905
    0.06
    LI
    0.06
    era
    0.06
    Activations Density 0.009%

    No Known Activations