© 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. 9-LLAMASCOPE-RES-131K
    11. 99270
    Prev
    Next
    INDEX
    Explanations

    words related to dental treatments or products

    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
    utt
    -0.08
    odd
    -0.07
    æº
    -0.07
    èĥŀ
    -0.07
     Invocation
    -0.07
    agas
    -0.07
    bsub
    -0.07
    isphere
    -0.07
    .gdx
    -0.06
     scratch
    -0.06
    POSITIVE LOGITS
    ouri
    0.08
    578
    0.06
    .snap
    0.06
     ref
    0.06
    _waiting
    0.06
     ì°©
    0.06
     Lent
    0.06
    iqu
    0.05
    Ref
    0.05
    asaki
    0.05
    Activations Density 0.000%

    No Known Activations