© 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 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. 87474
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Jesse" 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
    loi
    -0.08
    naments
    -0.07
    iesen
    -0.07
    hetto
    -0.07
    iesta
    -0.07
    ichern
    -0.07
    uste
    -0.07
    itesi
    -0.07
    esel
    -0.07
    \<^
    -0.07
    POSITIVE LOGITS
    amine
    0.07
    Äįan
    0.06
    ALT
    0.06
    mer
    0.06
    itant
    0.06
     Rav
    0.06
    guards
    0.06
    embro
    0.06
    PCP
    0.06
    holder
    0.06
    Activations Density 0.004%

    No Known Activations