© 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. 95563
    Prev
    Next
    INDEX
    Explanations

    variations of the word "act" and phrases related to behavior

    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
    rections
    -0.07
    ãĤ·ãĤ§
    -0.07
    yles
    -0.07
    kuk
    -0.07
    owe
    -0.07
    inton
    -0.07
    chodu
    -0.07
    hiba
    -0.07
    assage
    -0.07
    idges
    -0.07
    POSITIVE LOGITS
     behalf
    0.08
     towards
    0.07
     upon
    0.07
     toward
    0.07
     differently
    0.07
     act
    0.07
     acts
    0.07
    uate
    0.07
     acted
    0.06
     Towards
    0.06
    Activations Density 0.022%

    No Known Activations