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

    Neuronpedia

    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. 39853
    Prev
    Next
    INDEX
    Explanations

    references to the reader or audience, particularly the word "you"

    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
    avit
    -0.07
    &T
    -0.07
    oret
    -0.06
    prit
    -0.06
     Kür
    -0.06
    å¸Ŀ
    -0.06
    recent
    -0.06
    -0.06
    ATRIX
    -0.06
    alte
    -0.06
    POSITIVE LOGITS
     unsus
    0.07
    ácil
    0.07
    pher
    0.07
    Them
    0.07
    /if
    0.06
     otherwise
    0.06
    LineStyle
    0.06
    rok
    0.06
    tas
    0.06
    .jp
    0.06
    Activations Density 0.008%

    No Known Activations