© 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. 69196
    Prev
    Next
    INDEX
    Explanations

    specific names or titles, particularly with the use of apostrophes

    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
     latter
    -0.09
    ’ta
    -0.09
    ’t
    -0.08
    loquent
    -0.08
    /or
    -0.08
    ffen
    -0.07
    å¿ĥ
    -0.07
    ’n
    -0.07
    ieee
    -0.07
    croft
    -0.07
    POSITIVE LOGITS
    ÂĿ
    0.09
    ÑįÑĤомÑĥ
    0.09
    adays
    0.08
    iversit
    0.08
    gether
    0.08
    nbsp
    0.08
    amp
    0.08
    wards
    0.08
    crease
    0.08
    /'
    0.07
    Activations Density 0.030%

    No Known Activations