© 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. 63074
    Prev
    Next
    INDEX
    Explanations

    metrics related to social media engagement and reach

    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
    archical
    -0.06
    uario
    -0.06
    ureau
    -0.06
     listings
    -0.06
     nominal
    -0.06
    fi
    -0.06
    208
    -0.06
    isto
    -0.06
    opis
    -0.06
     Nom
    -0.06
    POSITIVE LOGITS
    _Abstract
    0.09
    arel
    0.07
    .binding
    0.07
    zza
    0.07
    IVERS
    0.07
    ivate
    0.07
    .fm
    0.07
    .Pointer
    0.07
     abstract
    0.07
    ÙĬÙĪÙĨ
    0.07
    Activations Density 0.001%

    No Known Activations