© 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. 59482
    Prev
    Next
    INDEX
    Explanations

    references to toxicity or harmful substances, particularly involving poison

    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
    ustin
    -0.07
    abouts
    -0.07
    gy
    -0.07
    aret
    -0.07
    infeld
    -0.06
    uz
    -0.06
    SizeMode
    -0.06
    luvÃŃ
    -0.06
    uplic
    -0.06
    usi
    -0.06
    POSITIVE LOGITS
    ously
    0.08
    ess
    0.07
    /to
    0.07
    ous
    0.07
    edImage
    0.07
    ivy
    0.07
    imbus
    0.07
    IFS
    0.07
    ned
    0.07
    ignet
    0.07
    Activations Density 0.005%

    No Known Activations