© 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. 69232
    Prev
    Next
    INDEX
    Explanations

    affirmative statements regarding actions or descriptions

    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
     Gig
    -0.05
     vice
    -0.05
     kä
    -0.05
    ä¸Ī
    -0.05
    PathVariable
    -0.05
    ìłĪ
    -0.05
     least
    -0.05
    entiful
    -0.05
    fo
    -0.05
     hollow
    -0.05
    POSITIVE LOGITS
    helm
    0.08
    Smarty
    0.07
    luet
    0.07
     fits
    0.07
     exciting
    0.07
    ümüz
    0.07
     minh
    0.07
    .fit
    0.07
    errat
    0.07
    ept
    0.07
    Activations Density 0.022%

    No Known Activations