© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 87015
    Prev
    Next
    INDEX
    Explanations

    instances of the contraction "I'd" related to personal experiences or assertions

    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
     доÑģ
    -0.07
    足
    -0.07
    ENN
    -0.06
    lds
    -0.06
     пеÑĢей
    -0.06
     mát
    -0.06
    plemented
    -0.06
    /ns
    -0.06
    ilib
    -0.06
    olds
    -0.06
    POSITIVE LOGITS
     been
    0.13
    been
    0.10
     be
    0.10
     Been
    0.09
    Been
    0.09
     sido
    0.08
     BEEN
    0.08
     come
    0.08
     become
    0.07
    -be
    0.07
    Activations Density 0.015%

    No Known Activations