© 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. 9-LLAMASCOPE-RES-131K
    11. 95813
    Prev
    Next
    INDEX
    Explanations

    clothing and loungewear items

    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
    aggio
    -0.07
    ixo
    -0.07
    iná
    -0.06
     bod
    -0.06
    ió
    -0.06
     divis
    -0.06
    ูà¹Ī
    -0.06
    inz
    -0.06
    jourd
    -0.06
     Tat
    -0.06
    POSITIVE LOGITS
    ares
    0.06
     LENG
    0.06
    idenav
    0.06
    imli
    0.06
    ÙĨتÛĮ
    0.06
    ITAL
    0.06
    .anchor
    0.06
    amas
    0.06
    urette
    0.06
    /py
    0.06
    Activations Density 0.004%

    No Known Activations