© 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. 103906
    Prev
    Next
    INDEX
    Explanations

    instances of high-intensity expressions or exclamations

    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
    etas
    -0.07
    unsch
    -0.07
    keterangan
    -0.07
    lew
    -0.06
    .GetObject
    -0.06
    esa
    -0.06
    _AG
    -0.06
    olina
    -0.06
    ắc
    -0.06
    LObject
    -0.06
    POSITIVE LOGITS
    istring
    0.06
    иденÑĤ
    0.06
    atta
    0.06
    avr
    0.06
    Closed
    0.06
    umhur
    0.06
    alley
    0.05
     closed
    0.05
     Closed
    0.05
     Highland
    0.05
    Activations Density 0.004%

    No Known Activations