© 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. 30928
    Prev
    Next
    INDEX
    Explanations

    gestures and actions related to creating or altering situations

    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
    inges
    -0.06
     localVar
    -0.06
    wik
    -0.06
    inya
    -0.06
    .NORMAL
    -0.06
    mis
    -0.06
    hawk
    -0.06
    ãĥ¼ãĥĭ
    -0.06
    æĭ¥
    -0.06
    FN
    -0.06
    POSITIVE LOGITS
     decisions
    0.06
    bons
    0.06
     typ
    0.06
    710
    0.06
     statement
    0.06
    ród
    0.06
    933
    0.06
    507
    0.06
     decision
    0.06
    anean
    0.06
    Activations Density 0.058%

    No Known Activations