© 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. 9-LLAMASCOPE-RES-131K
    11. 96472
    Prev
    Next
    INDEX
    Explanations

    calls to action related to purchasing or booking products and services

    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
    paths
    -0.06
     liebe
    -0.06
    edicine
    -0.06
    bits
    -0.06
    kin
    -0.06
    arte
    -0.06
     ActiveForm
    -0.06
    ictory
    -0.06
     Moms
    -0.06
    quences
    -0.05
    POSITIVE LOGITS
    εÏį
    0.07
    annes
    0.07
    orrent
    0.07
    Äįka
    0.07
    ì¡
    0.07
     пÑĢок
    0.06
    :animated
    0.06
    cxx
    0.06
    εÏħ
    0.06
    BOTTOM
    0.06
    Activations Density 0.023%

    No Known Activations