© 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. 15-LLAMASCOPE-RES-131K
    11. 86786
    Prev
    Next
    INDEX
    Explanations

    instances of the word "who" in various grammatical 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
    ty
    -0.08
    ching
    -0.08
    ting
    -0.07
    AM
    -0.07
    ouch
    -0.07
    dit
    -0.07
    mente
    -0.07
    õi
    -0.07
    asar
    -0.06
    leaning
    -0.06
    POSITIVE LOGITS
     else
    0.09
    ewith
    0.09
    IGHL
    0.07
    soever
    0.07
    erta
    0.07
    uchos
    0.07
    croft
    0.06
    else
    0.06
    copy
    0.06
     escap
    0.06
    Activations Density 0.036%

    No Known Activations