© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96524
    Prev
    Next
    INDEX
    Explanations

    words related to injury or harm

    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
    Phoenix
    -0.06
    ville
    -0.06
    quest
    -0.06
     Phoenix
    -0.06
    ستگÛĮ
    -0.06
    ileen
    -0.06
    ادر
    -0.06
    wards
    -0.06
    ward
    -0.06
    968
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    AU
    0.07
     è»
    0.07
    utton
    0.06
    ̣
    0.06
     cá»Ļng
    0.06
    atische
    0.06
     Gravity
    0.06
     MainAxisAlignment
    0.06
    jÃł
    0.06
    Activations Density 0.000%

    No Known Activations