© 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 EvalsExportsAPI 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. 40367
    Prev
    Next
    INDEX
    Explanations

    quotes from public officials and their statistical references

    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
    ani
    -0.07
    祥
    -0.07
    acher
    -0.06
    .appspot
    -0.06
    aylor
    -0.06
     Comedy
    -0.06
    Ta
    -0.06
    illac
    -0.06
    ivatel
    -0.06
    ibur
    -0.06
    POSITIVE LOGITS
     President
    0.09
     president
    0.08
     said
    0.07
     Mayor
    0.07
    President
    0.07
     joint
    0.07
    349
    0.07
    noinspection
    0.07
    said
    0.07
    -President
    0.07
    Activations Density 0.048%

    No Known Activations