© 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. 94288
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating scores or statistics

    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
    neau
    -0.07
    anoia
    -0.07
    pha
    -0.06
    mpp
    -0.06
    bart
    -0.06
    phan
    -0.06
     Foreign
    -0.06
    /Table
    -0.06
    ÑĥÑĩ
    -0.06
    quine
    -0.06
    POSITIVE LOGITS
    adium
    0.07
    hetto
    0.07
    lems
    0.07
    dam
    0.07
    rical
    0.06
    Subscribe
    0.06
    _defs
    0.06
    ä¸Ī
    0.06
     opport
    0.06
    گاÙĩÛĮ
    0.06
    Activations Density 0.000%

    No Known Activations