© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123271
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to sets and their properties

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    emiz
    -0.07
    MOTE
    -0.07
    ikler
    -0.07
    adÄĽ
    -0.07
    arna
    -0.07
    /catalog
    -0.06
    缤
    -0.06
    OCK
    -0.06
    cba
    -0.06
    voir
    -0.06
    POSITIVE LOGITS
    /not
    0.06
    eto
    0.06
    irement
    0.06
    rych
    0.06
    oro
    0.06
    κει
    0.06
    ÏĨÏħ
    0.06
    FFE
    0.06
    kop
    0.06
    iff
    0.06
    Activations Density 0.021%

    No Known Activations