© 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. 116823
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating actions or achievements

    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
     tslib
    -0.07
    afen
    -0.07
    qui
    -0.07
    itler
    -0.07
    orage
    -0.07
    ounced
    -0.07
    ÅĽcie
    -0.06
    Abs
    -0.06
    .vn
    -0.06
     köln
    -0.06
    POSITIVE LOGITS
    oes
    0.06
    orte
    0.06
    BAT
    0.06
    onga
    0.06
     previously
    0.06
    804
    0.06
    arte
    0.06
     Sche
    0.06
     Tk
    0.05
    @@
    0.05
    Activations Density 0.001%

    No Known Activations