© 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. 31067
    Prev
    Next
    INDEX
    Explanations

    terms related to toxins and health hazards associated with substances

    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
    ERRU
    -0.08
    reon
    -0.08
    unny
    -0.07
    èĻŁ
    -0.07
    lub
    -0.07
    unca
    -0.07
    duk
    -0.07
    669
    -0.07
    isas
    -0.07
    ZR
    -0.06
    POSITIVE LOGITS
     poisoning
    0.11
     poisonous
    0.09
     toxic
    0.09
     Poison
    0.09
     poison
    0.09
     toxicity
    0.08
     poisoned
    0.08
     Toxic
    0.08
     ingestion
    0.08
     intoxic
    0.07
    Activations Density 0.022%

    No Known Activations