© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80559
    Prev
    Next
    INDEX
    Explanations

    references to the location or name "Baker."

    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
    nex
    -0.08
    bubble
    -0.07
    tep
    -0.07
    chez
    -0.07
    gle
    -0.07
    tuk
    -0.07
    infeld
    -0.06
    ez
    -0.06
    ueur
    -0.06
    ácil
    -0.06
    POSITIVE LOGITS
    stown
    0.09
    ies
    0.08
    horn
    0.07
    ly
    0.07
    IES
    0.07
    liness
    0.07
    lee
    0.07
    thumb
    0.06
    chluss
    0.06
     soda
    0.06
    Activations Density 0.011%

    No Known Activations