© 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. 96293
    Prev
    Next
    INDEX
    Explanations

    postal codes and related geographic identifiers

    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
    iks
    -0.07
    OrNil
    -0.06
    åºķ
    -0.06
     Nug
    -0.06
     oven
    -0.06
    -SA
    -0.06
    anmar
    -0.06
    ys
    -0.05
     moons
    -0.05
     sab
    -0.05
    POSITIVE LOGITS
     actionTypes
    0.07
    ibal
    0.07
     Bez
    0.07
    CommandLine
    0.07
    /Dk
    0.06
    (IServiceCollection
    0.06
    ewolf
    0.06
    ÏĥÏī
    0.06
    еж
    0.06
    _insn
    0.06
    Activations Density 0.000%

    No Known Activations