© 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. 41674
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant actions or events

    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
     Bilg
    -0.06
    hoff
    -0.06
    332
    -0.06
    eya
    -0.06
    /Library
    -0.06
    382
    -0.06
     Kr
    -0.06
    PI
    -0.06
    ÏĢλ
    -0.05
    оÑĤÑĭ
    -0.05
    POSITIVE LOGITS
    engu
    0.07
    ãĤªãĥ³
    0.07
    ãĥĭãĤ¢
    0.07
    cente
    0.07
    etin
    0.07
    ournée
    0.07
     Hij
    0.07
    ertest
    0.06
    lesia
    0.06
    _NC
    0.06
    Activations Density 0.000%

    No Known Activations