© 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. 5-LLAMASCOPE-RES-131K
    11. 126692
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "pose," particularly in contexts related to photography or modeling

    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
    thew
    -0.07
    ÑŁ
    -0.07
    nea
    -0.07
    isay
    -0.07
    typeorm
    -0.07
    ellen
    -0.07
     Scri
    -0.07
    laps
    -0.07
     Gazette
    -0.06
    ilos
    -0.06
    POSITIVE LOGITS
    out
    0.07
    iful
    0.06
    unkt
    0.06
    ings
    0.06
    Clr
    0.06
    ÌĪ
    0.06
    lednÃŃ
    0.06
    дин
    0.06
    ëģĶ
    0.06
     Neb
    0.06
    Activations Density 0.003%

    No Known Activations