© 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. 15-LLAMASCOPE-RES-131K
    11. 90530
    Prev
    Next
    INDEX
    Explanations

    a specific format of postal or registration codes

    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
    ium
    -0.06
     Gibson
    -0.06
     Corm
    -0.06
    468
    -0.05
    wards
    -0.05
    inch
    -0.05
     precinct
    -0.05
     relocated
    -0.05
    Cog
    -0.05
     kilometres
    -0.05
    POSITIVE LOGITS
    #ad
    0.08
    keh
    0.07
     полÑı
    0.07
    виÑĩай
    0.07
     taÅŁ
    0.07
    ãĥ»ãĥ»ãĥ»↵↵
    0.07
    xo
    0.07
    ometr
    0.07
    صÙĪر
    0.07
    /OR
    0.06
    Activations Density 0.002%

    No Known Activations