© 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. 103872
    Prev
    Next
    INDEX
    Explanations

    formatting elements related to publication or documentation

    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
    anio
    -0.07
    -An
    -0.07
    achi
    -0.07
    ttp
    -0.07
    Ñĥй
    -0.06
    igits
    -0.06
    DataURL
    -0.06
    :animated
    -0.06
    ulis
    -0.06
    uan
    -0.06
    POSITIVE LOGITS
    aker
    0.06
     set
    0.06
     sets
    0.06
    AKER
    0.06
     McGu
    0.05
    arend
    0.05
    é¢
    0.05
    ç£
    0.05
    edn
    0.05
    igham
    0.05
    Activations Density 0.002%

    No Known Activations