© 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. 29443
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Becky" or variations thereof

    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
    yers
    -0.07
    ye
    -0.07
    leo
    -0.07
    esi
    -0.07
    à¥ĩहर
    -0.06
    fram
    -0.06
    stin
    -0.06
    Îŀ
    -0.06
    gebra
    -0.06
    HIR
    -0.06
    POSITIVE LOGITS
    Sharper
    0.08
    olds
    0.07
    ording
    0.06
    ann
    0.06
    emer
    0.06
    emy
    0.06
    oint
    0.06
    athan
    0.06
    ardo
    0.06
     bab
    0.06
    Activations Density 0.001%

    No Known Activations