© 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. 77363
    Prev
    Next
    INDEX
    Explanations

    expressions of violence and strong emotions towards others

    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
    ctic
    -0.07
    алеж
    -0.06
    yles
    -0.06
     Damen
    -0.06
    wert
    -0.06
    AVED
    -0.06
     Zahl
    -0.06
    ÑĨеÑģ
    -0.06
    ÑĢо
    -0.06
     Larger
    -0.06
    POSITIVE LOGITS
    owel
    0.07
     throat
    0.07
    exter
    0.07
    ugas
    0.07
     tongue
    0.06
     Tong
    0.06
     bindActionCreators
    0.06
     hale
    0.06
     Cyr
    0.06
     hung
    0.06
    Activations Density 0.039%

    No Known Activations