© 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. 9-LLAMASCOPE-RES-131K
    11. 98557
    Prev
    Next
    INDEX
    Explanations

    patterns or structures that indicate similarities and common features in various contexts

    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
    one
    -0.07
    ÙħÙĬ
    -0.07
    yre
    -0.07
    arris
    -0.07
    etti
    -0.06
    standing
    -0.06
    ibile
    -0.06
    ened
    -0.06
    p
    -0.06
    hog
    -0.06
    POSITIVE LOGITS
     alike
    0.07
    롱
    0.07
    Across
    0.07
    isphere
    0.06
    igu
    0.06
     Across
    0.06
     across
    0.06
    subtract
    0.06
    MinMax
    0.06
    serializer
    0.06
    Activations Density 0.065%

    No Known Activations