© 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. 120221
    Prev
    Next
    INDEX
    Explanations

    statements that clarify authorship or disclaim responsibility for content

    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
    ki
    -0.07
     Ash
    -0.06
    زÙħ
    -0.06
    inel
    -0.06
    hci
    -0.06
    ellen
    -0.06
    pite
    -0.06
    vester
    -0.06
    веÑī
    -0.06
    oby
    -0.06
    POSITIVE LOGITS
     views
    0.11
     opinions
    0.11
    views
    0.10
     opinion
    0.09
     Views
    0.09
     opin
    0.09
    op
    0.08
    Views
    0.08
     Opinion
    0.07
    inions
    0.07
    Activations Density 0.002%

    No Known Activations