© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86423
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "non-" in various 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
    bage
    -0.08
    mpeg
    -0.08
    alleries
    -0.08
    gger
    -0.08
     Jako
    -0.08
    igner
    -0.08
    avra
    -0.08
    fillType
    -0.07
     Incontri
    -0.07
    .trip
    -0.07
    POSITIVE LOGITS
    0.07
     Downtown
    0.06
     Bart
    0.06
    ansi
    0.06
    ara
    0.06
     carrier
    0.06
    ito
    0.05
    ana
    0.05
    ,
    0.05
    .
    0.05
    Activations Density 0.015%

    No Known Activations