© 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. 17-LLAMASCOPE-RES-131K
    11. 60116
    Prev
    Next
    INDEX
    Explanations

    references to geographic regions or local government entities

    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
    lide
    -0.07
    iah
    -0.07
     proto
    -0.06
    987
    -0.06
    oise
    -0.06
     Marketable
    -0.06
    angs
    -0.06
    ault
    -0.06
    odor
    -0.06
    asant
    -0.06
    POSITIVE LOGITS
     jadx
    0.08
    adele
    0.08
    -count
    0.07
     County
    0.07
    esModule
    0.07
    éĥ¡
    0.07
    ØŃÙĬ
    0.07
    /count
    0.07
    /Branch
    0.06
    iffin
    0.06
    Activations Density 0.002%

    No Known Activations