© 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. 88581
    Prev
    Next
    INDEX
    Explanations

    themes related to injustice and oppression

    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
    ecal
    -0.06
    lify
    -0.06
    iero
    -0.06
    usercontent
    -0.06
    GraphNode
    -0.06
     wis
    -0.06
    uilt
    -0.06
    å¿
    -0.06
    ãĤĪãģĨãģ«
    -0.06
    &view
    -0.06
    POSITIVE LOGITS
     treatment
    0.07
     brow
    0.07
    iveness
    0.07
    reatment
    0.07
    resas
    0.07
    REAM
    0.07
    oldt
    0.06
    isor
    0.06
    ÑĢаÐ
    0.06
     Treatment
    0.06
    Activations Density 0.020%

    No Known Activations