© 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. 123505
    Prev
    Next
    INDEX
    Explanations

    letters, numbers, and punctuations that indicate specific formatting or symbolic categories

    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
    AdapterManager
    -0.08
    ulty
    -0.08
    Å¡k
    -0.08
    .DataBind
    -0.07
    iju
    -0.07
    .bpm
    -0.07
    StandardItem
    -0.07
    _MUT
    -0.07
    ZN
    -0.07
    iscal
    -0.07
    POSITIVE LOGITS
    .
    0.06
     Both
    0.06
     alone
    0.05
     demonstr
    0.05
     ph
    0.05
     both
    0.05
    alternate
    0.05
    unas
    0.05
     Stark
    0.05
     Gos
    0.05
    Activations Density 0.002%

    No Known Activations