© 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. 108091
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronoun "we" and related verb forms

    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
    ÃŃsk
    -0.08
    ãĥįãĥ«
    -0.07
     yans
    -0.07
     hala
    -0.07
    é¨İ
    -0.07
    _resolver
    -0.07
     æ
    -0.07
     Gene
    -0.07
    acket
    -0.07
    gene
    -0.07
    POSITIVE LOGITS
    ibil
    0.07
     offer
    0.06
     design
    0.06
    ssp
    0.06
     stealth
    0.06
    erece
    0.06
     editorial
    0.06
    otts
    0.06
     finished
    0.06
    arend
    0.06
    Activations Density 0.114%

    No Known Activations