© 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. 57429
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or setting descriptions

    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
    uder
    -0.07
    endas
    -0.07
    phas
    -0.06
    _VALUES
    -0.06
    lee
    -0.06
    uter
    -0.06
    asin
    -0.06
     kolo
    -0.06
    lea
    -0.06
     çľ
    -0.06
    POSITIVE LOGITS
    ermo
    0.07
     Incontri
    0.07
    iyet
    0.07
    èĮĤ
    0.07
    874
    0.07
    edik
    0.07
    ekli
    0.07
    Queryable
    0.06
    squ
    0.06
     Orr
    0.06
    Activations Density 0.005%

    No Known Activations