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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90502
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of denial

    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
    sch
    -0.07
    ÑĢеж
    -0.07
    owie
    -0.07
    ening
    -0.07
    umen
    -0.07
     Byl
    -0.07
    ichi
    -0.06
    nest
    -0.06
    ets
    -0.06
     vé
    -0.06
    POSITIVE LOGITS
    asca
    0.07
    cular
    0.07
    AYOUT
    0.06
     çĬ
    0.06
    .lib
    0.06
    (strict
    0.06
    ippet
    0.06
    irler
    0.06
    zed
    0.06
    cono
    0.06
    Activations Density 0.037%

    No Known Activations