© 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. 17-LLAMASCOPE-RES-131K
    11. 77828
    Prev
    Next
    INDEX
    Explanations

    phrases expressing potential interest or consideration

    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
    ippy
    -0.06
    lion
    -0.06
    ULSE
    -0.06
     Beit
    -0.06
     Tomorrow
    -0.06
    amina
    -0.06
     ifs
    -0.06
     Rosen
    -0.06
    ÏĦα
    -0.05
    deme
    -0.05
    POSITIVE LOGITS
     interest
    0.08
    chwitz
    0.08
     interests
    0.07
    Interest
    0.07
    opp
    0.07
     Interest
    0.07
    alter
    0.07
    опаÑģ
    0.07
    Interop
    0.07
     migrationBuilder
    0.07
    Activations Density 0.003%

    No Known Activations