© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106237
    Prev
    Next
    INDEX
    Explanations

    geographical locations and references within the text

    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
    hee
    -0.07
    rael
    -0.07
    pekt
    -0.07
    ulg
    -0.07
    ipe
    -0.06
     //!<
    -0.06
    unik
    -0.06
    Inspect
    -0.06
     пеÑĢеÑģ
    -0.06
    elf
    -0.06
    POSITIVE LOGITS
    äll
    0.08
    ÏĥÏĥ
    0.06
    ummings
    0.06
    untime
    0.06
     United
    0.06
    ometown
    0.06
     parental
    0.06
    achusetts
    0.06
    igers
    0.06
    ово
    0.06
    Activations Density 0.003%

    No Known Activations