© 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. 61073
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thunder" and its variations or related terms

    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
    Ùģس
    -0.08
    avou
    -0.08
    NEY
    -0.07
    shm
    -0.07
    MMdd
    -0.07
    ãĤ¢ãĥ¼
    -0.07
    agos
    -0.07
    isposable
    -0.07
    gear
    -0.07
    ependency
    -0.07
    POSITIVE LOGITS
    ous
    0.10
    storms
    0.09
    storm
    0.09
    bolt
    0.09
    uous
    0.07
    str
    0.07
    %X
    0.07
    oen
    0.06
    ial
    0.06
    ious
    0.06
    Activations Density 0.004%

    No Known Activations