© 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. 17-LLAMASCOPE-RES-131K
    11. 74972
    Prev
    Next
    INDEX
    Explanations

    instances of individuals taking action to assist others in distress

    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
    jom
    -0.07
    że
    -0.07
    anki
    -0.07
    egt
    -0.07
    IALIZED
    -0.07
    aldi
    -0.07
    ä¼ı
    -0.07
    ottes
    -0.07
    usercontent
    -0.07
    .hwp
    -0.07
    POSITIVE LOGITS
     intervention
    0.11
     rescue
    0.10
     helping
    0.10
     intervene
    0.10
     resc
    0.10
     help
    0.10
     interventions
    0.09
     interven
    0.09
     intervened
    0.09
     Intervention
    0.08
    Activations Density 0.081%

    No Known Activations