© 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. 94220
    Prev
    Next
    INDEX
    Explanations

    references to general categories or objects

    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
    activex
    -0.09
     )↵↵↵↵↵↵↵↵
    -0.08
    jay
    -0.08
    ÑĪкÑĥ
    -0.07
    ipeg
    -0.07
    elmet
    -0.07
    lsru
    -0.07
    Ñıб
    -0.07
    (æĹ¥
    -0.07
    igrams
    -0.07
    POSITIVE LOGITS
    bee
    0.06
     Davidson
    0.06
    fst
    0.06
    ordo
    0.06
     ed
    0.06
     d
    0.05
     Byron
    0.05
     lax
    0.05
    E
    0.05
    viso
    0.05
    Activations Density 0.021%

    No Known Activations