© 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. 9-LLAMASCOPE-RES-131K
    11. 96906
    Prev
    Next
    INDEX
    Explanations

    the phrase "up," particularly in various contexts

    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
    unj
    -0.08
    ambre
    -0.08
    /or
    -0.07
    oret
    -0.07
    bedo
    -0.06
    nal
    -0.06
    ateria
    -0.06
    pai
    -0.06
    ruba
    -0.06
    aeper
    -0.06
    POSITIVE LOGITS
    edException
    0.08
    -ÑĤаки
    0.07
    ìĬ¨
    0.06
    rightness
    0.06
     Crab
    0.06
    ä¸įäºĨ
    0.06
    sehen
    0.06
    -fashioned
    0.06
     resort
    0.06
     EVAL
    0.06
    Activations Density 0.006%

    No Known Activations