© 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. 22-LLAMASCOPE-RES-131K
    11. 3939
    Prev
    Next
    INDEX
    Explanations

    commands and prompts related to writing, reviews, and comments

    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
    æľĽ
    -0.06
    sak
    -0.06
     anth
    -0.06
     bound
    -0.06
    ___
    -0.05
    unning
    -0.05
    langs
    -0.05
     Pav
    -0.05
    ish
    -0.05
    oms
    -0.05
    POSITIVE LOGITS
    resse
    0.08
    ancel
    0.08
    pmat
    0.07
    strcasecmp
    0.06
    enci
    0.06
    VES
    0.06
    pis
    0.06
     cân
    0.06
    Brief
    0.06
    endcode
    0.06
    Activations Density 0.004%

    No Known Activations