© 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. 78439
    Prev
    Next
    INDEX
    Explanations

    phrases related to interactions or engagements

    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
    estatus
    -0.08
    osu
    -0.07
    हन
    -0.07
    /tiny
    -0.07
    ãĤ
    -0.07
    oner
    -0.07
    quo
    -0.07
    isl
    -0.07
    Ù
    -0.07
    ego
    -0.07
    POSITIVE LOGITS
    ives
    0.09
    uality
    0.08
    ively
    0.08
    ivate
    0.08
    ative
    0.08
    ype
    0.07
    iveness
    0.07
    al
    0.07
    uator
    0.07
     between
    0.07
    Activations Density 0.017%

    No Known Activations