© 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. 62880
    Prev
    Next
    INDEX
    Explanations

    words associated with explosions or loud sounds

    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
    shima
    -0.07
    seau
    -0.07
     latter
    -0.06
    attro
    -0.06
    Ùĥر
    -0.06
    ##_
    -0.06
    iles
    -0.06
    idence
    -0.06
    finity
    -0.06
    Ä°s
    -0.06
    POSITIVE LOGITS
    çĦ¶
    0.08
    guns
    0.07
    ovol
    0.07
    wagon
    0.07
    urbation
    0.07
    ingly
    0.07
    jang
    0.06
     Paren
    0.06
    rod
    0.06
    igation
    0.06
    Activations Density 0.008%

    No Known Activations