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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90793
    Prev
    Next
    INDEX
    Explanations

    actions associated with physical violence and aggression

    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
    çīĩ
    -0.07
    atics
    -0.07
    act
    -0.07
    habi
    -0.07
    pez
    -0.07
    .CR
    -0.07
    erc
    -0.07
    iÅ¡tÄĽ
    -0.06
    imers
    -0.06
    utt
    -0.06
    POSITIVE LOGITS
     unspecified
    0.07
    ulary
    0.06
    sob
    0.06
     unnamed
    0.06
     sap
    0.06
     s
    0.05
    ushi
    0.05
     physical
    0.05
    etag
    0.05
    leÅŁ
    0.05
    Activations Density 0.012%

    No Known Activations