© 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. 126932
    Prev
    Next
    INDEX
    Explanations

    references to toilets and related facilities

    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
    edly
    -0.07
    873
    -0.06
    f
    -0.06
    s
    -0.06
    fn
    -0.06
    adr
    -0.06
    887
    -0.06
     provid
    -0.06
    ley
    -0.06
    aging
    -0.06
    POSITIVE LOGITS
    ulumi
    0.09
    laz
    0.08
    gate
    0.08
    inox
    0.07
    urette
    0.07
    nict
    0.07
     пÑĢоб
    0.07
    imestep
    0.07
    ANDLE
    0.07
    chos
    0.07
    Activations Density 0.003%

    No Known Activations