© 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. 14371
    Prev
    Next
    INDEX
    Explanations

    references to compliance with regulations or laws

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    nett
    -0.07
    念
    -0.06
    ellung
    -0.06
    orthand
    -0.06
    stable
    -0.06
    nest
    -0.06
    pom
    -0.06
    ãĤ¥
    -0.06
    allen
    -0.06
    leared
    -0.06
    POSITIVE LOGITS
    ìłł
    0.08
    ément
    0.07
     with
    0.07
    inders
    0.07
    zÄħd
    0.07
    WithString
    0.07
     strictly
    0.07
    ãĤ¤ãĥī
    0.06
    .rules
    0.06
    chsel
    0.06
    Activations Density 0.004%

    No Known Activations