© 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. 42364
    Prev
    Next
    INDEX
    Explanations

    references to various sports, athletic activities, and artistic disciplines

    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
    ateria
    -0.07
    ross
    -0.06
    tesy
    -0.06
    yna
    -0.06
    vailable
    -0.06
    á»±a
    -0.06
    su
    -0.06
    oko
    -0.06
    дÑĸл
    -0.06
    éģķãģĦ
    -0.06
    POSITIVE LOGITS
    RootElement
    0.06
    ardım
    0.06
     jobject
    0.06
    ëĶ©
    0.06
    .Qual
    0.06
     PY
    0.06
    ÎijÎł
    0.06
    -catching
    0.06
    ordum
    0.06
    UGHT
    0.05
    Activations Density 0.068%

    No Known Activations