© 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. 80368
    Prev
    Next
    INDEX
    Explanations

    references to political entities and 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
    ABCDEFGHI
    -0.07
    jug
    -0.07
    ante
    -0.07
     Jug
    -0.07
    ivec
    -0.07
    hip
    -0.06
    llib
    -0.06
    sted
    -0.06
    \DependencyInjection
    -0.06
    شت
    -0.06
    POSITIVE LOGITS
     should
    0.21
    should
    0.19
    Should
    0.17
     ought
    0.17
     Should
    0.17
     shouldn
    0.16
    _should
    0.15
     SHOULD
    0.14
    åºĶ该
    0.14
    .should
    0.13
    Activations Density 0.037%

    No Known Activations