© 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. 80173
    Prev
    Next
    INDEX
    Explanations

    keywords related to searching for information or images

    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
     Kraj
    -0.07
    erval
    -0.07
    âĺĨ
    -0.07
    ,exports
    -0.07
    enal
    -0.07
    emodel
    -0.07
    mamak
    -0.07
     ìłĪ
    -0.07
    (SC
    -0.06
    ipse
    -0.06
    POSITIVE LOGITS
     request
    0.08
     requests
    0.08
    request
    0.07
    ulia
    0.07
    igans
    0.07
    :request
    0.07
    clerosis
    0.07
    .request
    0.06
    \Query
    0.06
     Fal
    0.06
    Activations Density 0.002%

    No Known Activations