© 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. 17110
    Prev
    Next
    INDEX
    Explanations

    references to aging or nostalgia in relation to cinema and performances

    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
    lobals
    -0.07
     Funk
    -0.06
    ulong
    -0.06
     geçir
    -0.06
    ÏĢι
    -0.06
    alom
    -0.06
    olars
    -0.06
    ansson
    -0.06
    umbo
    -0.06
    (strict
    -0.06
    POSITIVE LOGITS
    ils
    0.07
    oir
    0.07
    etik
    0.07
    eme
    0.06
     Hansen
    0.06
    ril
    0.06
    ittel
    0.06
     Leone
    0.06
    Ú¯ÛĮر
    0.06
    elda
    0.06
    Activations Density 0.000%

    No Known Activations