© 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. 71259
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional and sensory experiences

    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
    loff
    -0.07
    indr
    -0.07
    ad
    -0.07
    /go
    -0.07
    umper
    -0.06
    ICO
    -0.06
    engo
    -0.06
     must
    -0.06
    ilians
    -0.06
     Sick
    -0.06
    POSITIVE LOGITS
    achs
    0.07
    Ñīи
    0.07
    inesis
    0.07
    /ws
    0.07
    anlık
    0.06
    iyas
    0.06
    uhan
    0.06
    _firestore
    0.06
    ppv
    0.06
    Fld
    0.06
    Activations Density 0.026%

    No Known Activations