© 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 EvalsExportsinterp-engineNEWAPI 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. 124012
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "more"

    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
     enough
    -0.08
     же
    -0.07
    zione
    -0.07
     Enough
    -0.06
    ãģ®ãģ¿
    -0.06
    _REF
    -0.06
    uby
    -0.06
    à¥Ĥब
    -0.06
    -mf
    -0.06
    shaw
    -0.06
    POSITIVE LOGITS
    -than
    0.09
    /new
    0.07
    leton
    0.07
    ths
    0.07
     cou
    0.07
     than
    0.06
    ató
    0.06
    -digit
    0.06
    wards
    0.06
    ceipt
    0.06
    Activations Density 0.013%

    No Known Activations