© 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. 3757
    Prev
    Next
    INDEX
    Explanations

    references to notable actors and film-related terminology

    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
     seperate
    -0.07
     âĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.07
    ported
    -0.07
    ugi
    -0.07
     inconvenient
    -0.06
    -esque
    -0.06
     seper
    -0.06
    _GB
    -0.06
    oples
    -0.06
     amongst
    -0.06
    POSITIVE LOGITS
    orial
    0.06
    rosse
    0.06
    ouz
    0.06
    wizard
    0.06
    wang
    0.06
    RootElement
    0.06
    Everybody
    0.06
    ondo
    0.06
    specs
    0.06
    UIView
    0.06
    Activations Density 0.000%

    No Known Activations