© 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. 56213
    Prev
    Next
    INDEX
    Explanations

    punctuation, particularly periods

    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
    queda
    -0.06
    andex
    -0.06
    aceutical
    -0.06
    oly
    -0.06
    olland
    -0.06
    213
    -0.06
    761
    -0.06
    _Impl
    -0.05
    roe
    -0.05
    æ¯Ľ
    -0.05
    POSITIVE LOGITS
    ertino
    0.06
    /jav
    0.06
    éĤ¦
    0.06
    _rl
    0.06
     Wyn
    0.06
    otas
    0.06
    #error
    0.06
    ungs
    0.06
    elu
    0.06
    eks
    0.06
    Activations Density 0.005%

    No Known Activations