© 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 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. 88526
    Prev
    Next
    INDEX
    Explanations

    descriptions of location and amenities related to hospitality and community features

    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
    ãģ¨ãģĵãĤį
    -0.06
    ayload
    -0.06
     rtrim
    -0.06
     inn
    -0.06
    ARD
    -0.06
     Hogan
    -0.06
    æ¯Ķ
    -0.06
    ule
    -0.06
     hom
    -0.05
     component
    -0.05
    POSITIVE LOGITS
    ollapse
    0.08
    álo
    0.07
     ^{°}
    0.07
    ÑĹна
    0.06
    ennen
    0.06
    osti
    0.06
     Nach
    0.06
    idy
    0.06
    alue
    0.06
    úmer
    0.06
    Activations Density 0.009%

    No Known Activations