© 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. 73845
    Prev
    Next
    INDEX
    Explanations

    words associated with emotional states and significant life concepts

    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
    aber
    -0.07
    riba
    -0.07
    erti
    -0.07
    ennie
    -0.07
    ération
    -0.07
    ifikasi
    -0.06
    /fa
    -0.06
    sak
    -0.06
    suz
    -0.06
    utsch
    -0.06
    POSITIVE LOGITS
    ful
    0.10
    able
    0.08
    ive
    0.08
    ically
    0.07
    ical
    0.07
    ous
    0.07
    full
    0.07
    osph
    0.07
    unate
    0.07
    ableObject
    0.07
    Activations Density 0.072%

    No Known Activations