© 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. 125738
    Prev
    Next
    INDEX
    Explanations

    questions that begin with "What" or "Who."

    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
    .opendaylight
    -0.06
    opian
    -0.06
     Fork
    -0.06
     詳細
    -0.06
    vers
    -0.06
    OUCH
    -0.06
     âĹĦ
    -0.06
    гÑĢад
    -0.06
    )animated
    -0.06
    anan
    -0.06
    POSITIVE LOGITS
     HttpMethod
    0.07
    .require
    0.07
    scri
    0.06
    ogg
    0.06
    ìĦł
    0.06
    Flutter
    0.06
    aket
    0.06
    меÑĤÑĮ
    0.06
    GetInt
    0.06
    toupper
    0.06
    Activations Density 0.009%

    No Known Activations