© 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. 29942
    Prev
    Next
    INDEX
    Explanations

    references to family movies and their viewing experiences

    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
     /
    -0.06
     st
    -0.06
     h
    -0.06
     Fucking
    -0.06
    011
    -0.06
     fuck
    -0.06
     imp
    -0.06
    'll
    -0.05
     via
    -0.05
     fucking
    -0.05
    POSITIVE LOGITS
    èo
    0.08
    ozilla
    0.08
     UIStoryboard
    0.08
    iqueta
    0.07
    .setStyle
    0.07
    ément
    0.07
    :animated
    0.07
     kli
    0.07
    ètre
    0.07
    getitem
    0.07
    Activations Density 0.003%

    No Known Activations