© 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. 73784
    Prev
    Next
    INDEX
    Explanations

    instances of the word "im" and its variations, indicating an emphasis on identity or characteristics

    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
    itel
    -0.07
    cai
    -0.06
    ady
    -0.06
    gor
    -0.06
    atement
    -0.06
    duced
    -0.06
    atomy
    -0.06
    QA
    -0.06
    indy
    -0.06
    åij³
    -0.05
    POSITIVE LOGITS
    othy
    0.11
    eload
    0.07
    yasal
    0.07
    462
    0.07
    isons
    0.07
    dio
    0.07
    ographed
    0.07
    ingen
    0.07
    ael
    0.07
    cox
    0.07
    Activations Density 0.023%

    No Known Activations