© 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. 118758
    Prev
    Next
    INDEX
    Explanations

    variations of the word "conditioned."

    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
    idf
    -0.07
    oftware
    -0.07
    -scalable
    -0.07
    jos
    -0.06
    овеÑĢ
    -0.06
    inee
    -0.06
    jom
    -0.06
    oko
    -0.06
    angan
    -0.06
    alat
    -0.06
    POSITIVE LOGITS
     ac
    0.06
     ben
    0.06
    ارة
    0.06
    ãĥ¬ãĥ³
    0.06
     Madd
    0.06
     Hilton
    0.06
    azel
    0.06
     Fus
    0.06
    zen
    0.05
    tion
    0.05
    Activations Density 0.000%

    No Known Activations