© 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. 104520
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Andy."

    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
    ercul
    -0.08
    GenerationStrategy
    -0.08
    (æľ¨
    -0.08
    neath
    -0.08
    овиÑĩ
    -0.07
    EmptyEntries
    -0.07
    ç·Ĵ
    -0.07
     Wired
    -0.07
    âķĹ
    -0.07
    ned
    -0.07
    POSITIVE LOGITS
    yst
    0.06
    bx
    0.06
    gram
    0.06
    ean
    0.06
    ergy
    0.05
    unta
    0.05
    bits
    0.05
    Å¡
    0.05
    ach
    0.05
     h
    0.05
    Activations Density 0.004%

    No Known Activations