© 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. 81172
    Prev
    Next
    INDEX
    Explanations

    references to the name "John" in various contexts

    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
    ãģĬãĤĬ
    -0.07
    )test
    -0.07
    -vous
    -0.07
    ensi
    -0.07
    coni
    -0.07
    ën
    -0.07
    ož
    -0.07
    erty
    -0.07
    luv
    -0.06
    elopment
    -0.06
    POSITIVE LOGITS
    son
    0.10
     himself
    0.09
    liness
    0.08
    alog
    0.08
    sWith
    0.07
    nie
    0.07
    ish
    0.07
    ERSHEY
    0.07
    sein
    0.07
    bies
    0.07
    Activations Density 0.023%

    No Known Activations