© 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. 127197
    Prev
    Next
    INDEX
    Explanations

    terms related to addiction treatment resources

    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
     ↵↵
    -0.07
     fon
    -0.07
    eryl
    -0.07
    ucken
    -0.07
    orners
    -0.07
    acket
    -0.07
    ture
    -0.07
    DSA
    -0.07
    acias
    -0.06
    URRE
    -0.06
    POSITIVE LOGITS
     substance
    0.06
    307
    0.06
    èĨ
    0.06
    λεκ
    0.06
    ANGUAGE
    0.06
    414
    0.06
     Dorm
    0.06
    owy
    0.05
     payment
    0.05
     cir
    0.05
    Activations Density 0.000%

    No Known Activations