© 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. 30172
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating value and purpose

    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
    om
    -0.06
    VIC
    -0.06
    apy
    -0.06
    htag
    -0.06
    ìļ±
    -0.06
    оÑģк
    -0.06
    åĨĴ
    -0.06
    kur
    -0.06
    ìĤ¬
    -0.06
    stance
    -0.06
    POSITIVE LOGITS
    warf
    0.07
    ña
    0.07
     unt
    0.06
     Unt
    0.06
    inaire
    0.06
    OffsetTable
    0.06
    ordan
    0.06
     Scarlet
    0.06
    ussen
    0.06
    ório
    0.06
    Activations Density 0.001%

    No Known Activations