© 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. 105430
    Prev
    Next
    INDEX
    Explanations

    URLs or web links in the text

    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
    ayan
    -0.06
     theory
    -0.06
     wholesale
    -0.05
     Graves
    -0.05
     Personal
    -0.05
    пов
    -0.05
    pan
    -0.05
    ven
    -0.05
    ÈĽ
    -0.05
    omi
    -0.05
    POSITIVE LOGITS
    dac
    0.08
     Drops
    0.07
    bfd
    0.07
    è¤
    0.07
    undles
    0.07
    ÏĦει
    0.07
    emento
    0.07
    @student
    0.07
    %S
    0.07
    è®®
    0.07
    Activations Density 0.000%

    No Known Activations