© 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 EvalsExportsAPI 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. 106519
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases that indicate actions or processes

    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
    heimer
    -0.07
    ulp
    -0.07
     Becker
    -0.07
    isay
    -0.07
    æĤ
    -0.06
    ãĥ£
    -0.06
    .codehaus
    -0.06
    oil
    -0.06
    ìļĶ
    -0.06
    tingham
    -0.06
    POSITIVE LOGITS
     matters
    0.07
     mÃł
    0.06
    kest
    0.06
    dül
    0.06
     же
    0.06
    akh
    0.06
    .gdx
    0.06
    egin
    0.06
    yy
    0.06
    robe
    0.06
    Activations Density 0.037%

    No Known Activations