© 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. 5091
    Prev
    Next
    INDEX
    Explanations

    job titles and contact information within a professional context

    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
    PRINTF
    -0.07
    \Migrations
    -0.07
    HELL
    -0.06
    emez
    -0.06
    aska
    -0.06
     Jew
    -0.06
    asca
    -0.06
     Management
    -0.06
    sess
    -0.06
    &o
    -0.06
    POSITIVE LOGITS
    odon
    0.07
    oleon
    0.07
    amo
    0.07
     email
    0.07
     Nimbus
    0.07
    à¤Ī
    0.07
    ets
    0.06
    email
    0.06
    mailto
    0.06
    å®Ŀ
    0.06
    Activations Density 0.068%

    No Known Activations