© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 77800
    Prev
    Next
    INDEX
    Explanations

    information related to acne treatment and medications

    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
    stk
    -0.07
    dent
    -0.07
    iple
    -0.06
    eton
    -0.06
    .Organization
    -0.06
     smr
    -0.06
     Arch
    -0.06
    yes
    -0.06
    fang
    -0.06
    elerinden
    -0.06
    POSITIVE LOGITS
    ÏĥÏį
    0.07
    práv
    0.07
    ellan
    0.07
    scription
    0.07
    bower
    0.07
     ná
    0.06
    ác
    0.06
     Skill
    0.06
    _gb
    0.06
    ãģŁãģĹ
    0.06
    Activations Density 0.012%

    No Known Activations