© 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. 27376
    Prev
    Next
    INDEX
    Explanations

    expressions or phrases indicating emotions, particularly those that convey surprise or shock

    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
    apo
    -0.07
    izi
    -0.07
    eva
    -0.07
    ife
    -0.07
    onnement
    -0.07
    uber
    -0.07
    bons
    -0.07
    ernal
    -0.07
    ugg
    -0.07
    ethyst
    -0.06
    POSITIVE LOGITS
    ctl
    0.07
    r
    0.07
    snap
    0.06
    hausen
    0.06
    annes
    0.06
     hum
    0.06
    inke
    0.06
     behalf
    0.06
    lig
    0.06
    lsen
    0.05
    Activations Density 0.020%

    No Known Activations