© 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. 88947
    Prev
    Next
    INDEX
    Explanations

    references to mythology and mythical concepts

    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
    er
    -0.07
    ilet
    -0.06
    zet
    -0.06
    eyh
    -0.06
    isoft
    -0.06
    inar
    -0.06
    noÅĽÄĩ
    -0.06
    arity
    -0.06
    ãĥ¼ãĥł
    -0.06
    ween
    -0.06
    POSITIVE LOGITS
    ological
    0.08
    ervo
    0.08
    olog
    0.08
    ellaneous
    0.07
    etic
    0.07
    ene
    0.07
    ril
    0.07
    oman
    0.07
    /my
    0.07
    os
    0.07
    Activations Density 0.006%

    No Known Activations