© 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 EvalsExportsAPI 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. 29269
    Prev
    Next
    INDEX
    Explanations

    expressions of confidence and optimism related to legislative actions or proposals

    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
    .Cmd
    -0.07
    ué
    -0.07
    itta
    -0.06
    -0.06
    hiba
    -0.06
    oulos
    -0.06
    oba
    -0.06
    rek
    -0.06
    uely
    -0.06
    ondo
    -0.06
    POSITIVE LOGITS
     eventual
    0.11
     eventually
    0.11
     soon
    0.11
     Soon
    0.09
     Eventually
    0.09
     will
    0.09
     forthcoming
    0.09
     outcome
    0.08
    Eventually
    0.08
     ultimately
    0.08
    Activations Density 0.043%

    No Known Activations