© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90416
    Prev
    Next
    INDEX
    Explanations

    expressions related to enjoyment or positive sentiment

    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
    /stat
    -0.06
     Gallagher
    -0.06
    ÙIJÙħ
    -0.06
    agger
    -0.06
    hoe
    -0.06
    dür
    -0.05
    caster
    -0.05
    ToFront
    -0.05
    pat
    -0.05
    èn
    -0.05
    POSITIVE LOGITS
    phis
    0.08
    ÏĦει
    0.07
    ¢åįķ
    0.07
    iar
    0.07
    iro
    0.07
    irth
    0.07
    oola
    0.07
    ably
    0.06
    endon
    0.06
    inite
    0.06
    Activations Density 0.003%

    No Known Activations