© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98915
    Prev
    Next
    INDEX
    Explanations

    instances of the word "smash" and its variations, indicating themes of destruction or impact

    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
    /from
    -0.08
    usz
    -0.08
    zial
    -0.07
    osemite
    -0.07
    obao
    -0.07
    AndPassword
    -0.07
    amm
    -0.07
    alet
    -0.07
    ally
    -0.07
    ISIBLE
    -0.07
    POSITIVE LOGITS
    wich
    0.07
    ulously
    0.07
    engers
    0.07
    elters
    0.07
    enger
    0.07
    -hit
    0.06
    ¢åįķ
    0.06
     vá»
    0.06
    urdy
    0.06
    ãĥ«ãĥī
    0.06
    Activations Density 0.008%

    No Known Activations