© 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. 30466
    Prev
    Next
    INDEX
    Explanations

    verbs associated with 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
    thin
    -0.07
    ying
    -0.06
    hti
    -0.06
    yx
    -0.06
    isure
    -0.06
    eping
    -0.06
     nghi
    -0.06
    aping
    -0.06
    ordin
    -0.06
    rog
    -0.06
    POSITIVE LOGITS
     been
    0.10
    ekk
    0.07
    been
    0.07
     BEEN
    0.07
    ombine
    0.07
    esub
    0.07
     me
    0.07
     to
    0.06
    wchar
    0.06
    bsub
    0.06
    Activations Density 0.002%

    No Known Activations