© 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. 1014
    Prev
    Next
    INDEX
    Explanations

    phrases describing physical injuries and trauma

    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
    indsight
    -0.07
    arde
    -0.07
    poÄįet
    -0.06
    umont
    -0.06
    γε
    -0.06
    ichier
    -0.06
    erce
    -0.06
    acobian
    -0.06
    먼
    -0.06
    :CGRect
    -0.06
    POSITIVE LOGITS
     queryInterface
    0.07
    iyan
    0.06
    jis
    0.06
    mites
    0.06
    gies
    0.06
    lant
    0.06
    frauen
    0.06
    ogenerated
    0.06
    achat
    0.06
    imet
    0.06
    Activations Density 0.012%

    No Known Activations