© 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. 17-LLAMASCOPE-RES-131K
    11. 16647
    Prev
    Next
    INDEX
    Explanations

    instances of ritualistic processes and emotional expressions

    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
    urar
    -0.07
     Mask
    -0.06
     abstract
    -0.06
    adel
    -0.06
    amage
    -0.06
     Val
    -0.06
     predecessors
    -0.06
    egl
    -0.06
    .mask
    -0.06
     mask
    -0.06
    POSITIVE LOGITS
    Uvs
    0.08
    ogany
    0.07
    .scalablytyped
    0.07
    jvu
    0.07
    Geom
    0.07
     itemprop
    0.06
    ìļ°ìĬ¤
    0.06
    виÑĤ
    0.06
    pu
    0.06
    INGTON
    0.06
    Activations Density 0.003%

    No Known Activations