© 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. 124001
    Prev
    Next
    INDEX
    Explanations

    numerical references, especially those related to the concepts of "two," "three," "four," "five," "six," and "nine."

    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
    -0.07
    ijo
    -0.06
     two
    -0.06
    -based
    -0.06
    190
    -0.06
    warts
    -0.06
    381
    -0.05
    iaux
    -0.05
     (
    -0.05
    istrovstvÃŃ
    -0.05
    POSITIVE LOGITS
    ième
    0.09
    fold
    0.08
    ToOne
    0.08
    onen
    0.08
    .sourceforge
    0.08
    Fold
    0.08
    ityEngine
    0.08
    ecko
    0.08
    ADVERTISEMENT
    0.08
     !:
    0.08
    Activations Density 0.025%

    No Known Activations