© 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. 14224
    Prev
    Next
    INDEX
    Explanations

    CSS formatting related to font weight and bold text

    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
    _IMPORTED
    -0.07
    _utilities
    -0.07
    ults
    -0.06
    ãĥŃãĤ°
    -0.06
    यर
    -0.06
    AWN
    -0.06
    istrat
    -0.06
    "]->
    -0.06
    ľ´
    -0.06
    generic
    -0.06
    POSITIVE LOGITS
    chas
    0.07
    iros
    0.07
    illo
    0.06
    ed
    0.06
    edImage
    0.06
    thren
    0.06
    iddles
    0.06
    248
    0.06
    ngth
    0.06
    er
    0.06
    Activations Density 0.002%

    No Known Activations