© 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. 98974
    Prev
    Next
    INDEX
    Explanations

    instances of terms related to vanishing or approaching zero in mathematical contexts

    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
    berman
    -0.07
    _defs
    -0.07
    ouver
    -0.07
    opoulos
    -0.07
    allet
    -0.06
    ondo
    -0.06
    reau
    -0.06
    hk
    -0.06
    .Interop
    -0.06
    uler
    -0.06
    POSITIVE LOGITS
    бÑĢа
    0.07
    /null
    0.06
    erti
    0.06
     Cheng
    0.06
    imals
    0.06
    ighted
    0.06
    lige
    0.06
    oley
    0.06
    utas
    0.06
    imity
    0.06
    Activations Density 0.090%

    No Known Activations