© 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. 76612
    Prev
    Next
    INDEX
    Explanations

    the word "pretty" and its variations in different contexts

    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
    stk
    -0.06
    ÑĪи
    -0.06
    st
    -0.06
    opis
    -0.06
    stag
    -0.06
    ÑģÑĮ
    -0.06
    esis
    -0.06
    ABLE
    -0.06
     suprem
    -0.06
    holes
    -0.06
    POSITIVE LOGITS
    -ÑĤаки
    0.09
    -boy
    0.09
     much
    0.09
     darn
    0.08
     ãĥĶ
    0.08
    byn
    0.07
    unda
    0.07
    fy
    0.07
    iness
    0.07
    ä¸ľè¥¿
    0.07
    Activations Density 0.016%

    No Known Activations