© 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 EvalsExportsinterp-engineNEWAPI 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. 117379
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate analysis and discussion, particularly in the context of societal or political issues

    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
    ãĤ¼
    -0.07
    lew
    -0.07
     rug
    -0.07
    tas
    -0.07
     anywhere
    -0.06
     пÑĢедÑĥÑģ
    -0.06
     комнаÑĤ
    -0.06
    adil
    -0.06
    Logic
    -0.06
    peq
    -0.06
    POSITIVE LOGITS
     why
    0.09
     how
    0.09
    how
    0.07
     whether
    0.07
    acci
    0.07
     impact
    0.07
    why
    0.06
     what
    0.06
     ways
    0.06
    isman
    0.06
    Activations Density 0.042%

    No Known Activations