© 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. 130578
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wish" and related terms indicating desires or preferences

    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
    VERSE
    -0.08
    hek
    -0.07
    oci
    -0.07
    /trans
    -0.06
    aldi
    -0.06
    ãĥ¬ãĥ¼
    -0.06
     Alam
    -0.06
    ILLISECONDS
    -0.06
    impse
    -0.06
    ziel
    -0.06
    POSITIVE LOGITS
    ful
    0.07
    dest
    0.06
    lists
    0.06
    ess
    0.06
    ì°¨
    0.06
     list
    0.06
    ë
    0.06
    zin
    0.05
    bellion
    0.05
    ç«ľ
    0.05
    Activations Density 0.000%

    No Known Activations