© 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. 56670
    Prev
    Next
    INDEX
    Explanations

    phrases indicating self-referential statements or personal reflections

    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
    itten
    -0.09
    272
    -0.07
    igm
    -0.06
    berries
    -0.06
    arios
    -0.06
     anthrop
    -0.06
     antic
    -0.06
    arius
    -0.06
    ighton
    -0.05
    ddy
    -0.05
    POSITIVE LOGITS
    asking
    0.09
    HUD
    0.08
     Heard
    0.07
    ê¶ģ
    0.07
    Segue
    0.07
    稿
    0.07
     questions
    0.06
     interest
    0.06
    presso
    0.06
    mant
    0.06
    Activations Density 0.021%

    No Known Activations