© 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. 116465
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "name"

    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
    ardon
    -0.07
    리ì§Ģ
    -0.07
    hint
    -0.06
    aston
    -0.06
    ottie
    -0.06
    resco
    -0.06
    Interop
    -0.06
    .ce
    -0.06
    outu
    -0.06
    iks
    -0.06
    POSITIVE LOGITS
    Balancer
    0.07
    ÙĤÙħ
    0.07
    setName
    0.06
     Brewer
    0.06
    erti
    0.06
    ValueCollection
    0.06
    amax
    0.06
    ÑĥÑĤи
    0.06
    Fonts
    0.06
    Nama
    0.06
    Activations Density 0.001%

    No Known Activations