© 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. 95911
    Prev
    Next
    INDEX
    Explanations

    references to bookmarked content or permalinks

    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
    emit
    -0.06
    umer
    -0.06
    ubl
    -0.06
    ONTAL
    -0.06
    kek
    -0.06
    anton
    -0.06
     herself
    -0.06
     dane
    -0.06
    .named
    -0.05
    actice
    -0.05
    POSITIVE LOGITS
    rowave
    0.07
    eyh
    0.06
    419
    0.06
    codegen
    0.06
     migrationBuilder
    0.06
    anlık
    0.06
    ypo
    0.06
    ogene
    0.06
    MBProgressHUD
    0.06
    foreground
    0.06
    Activations Density 0.001%

    No Known Activations