© 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. 91954
    Prev
    Next
    INDEX
    Explanations

    relationships involving authorship or attribution in texts

    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
    zzo
    -0.08
    itarian
    -0.07
    eldorf
    -0.07
    uploads
    -0.07
     diamond
    -0.06
     Shade
    -0.06
     wav
    -0.06
    werp
    -0.06
    quia
    -0.06
    cluded
    -0.06
    POSITIVE LOGITS
    ÑĪев
    0.06
    ÅĽ
    0.06
     supply
    0.06
    ajas
    0.06
     Anthrop
    0.06
     pall
    0.06
     Keller
    0.06
    ÑĢод
    0.06
    анÑĮ
    0.06
    ãĤĤãĤĬ
    0.06
    Activations Density 0.004%

    No Known Activations