© 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. 103861
    Prev
    Next
    INDEX
    Explanations

    references to bands or musical groups

    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
    yah
    -0.08
    екÑĤÑĥ
    -0.08
    loh
    -0.08
    edes
    -0.07
    abeth
    -0.07
     Bapt
    -0.07
    OutOfBounds
    -0.07
    uez
    -0.07
    cury
    -0.07
    ober
    -0.07
    POSITIVE LOGITS
    wagon
    0.12
    ana
    0.09
    width
    0.09
    anna
    0.07
    ANA
    0.07
    ura
    0.07
    ale
    0.07
    ital
    0.07
    it
    0.06
    ži
    0.06
    Activations Density 0.015%

    No Known Activations