© 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. 31201
    Prev
    Next
    INDEX
    Explanations

    expressions of strong negative emotions

    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
    ales
    -0.07
    sic
    -0.06
    aff
    -0.06
    _repr
    -0.06
    urre
    -0.06
     Tort
    -0.06
    lisi
    -0.06
     impulse
    -0.06
    interest
    -0.06
    ize
    -0.06
    POSITIVE LOGITS
     about
    0.07
    angu
    0.07
    loss
    0.07
    ãĥ©ãĥ³ãĤ¹
    0.07
    landers
    0.07
    .about
    0.07
    orque
    0.07
     å®®
    0.07
     migrationBuilder
    0.07
    ActionButton
    0.07
    Activations Density 0.019%

    No Known Activations