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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71436
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical dosages and forms

    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
    oji
    -0.07
    lage
    -0.07
    UNET
    -0.07
    اذ
    -0.06
    ichen
    -0.06
    blo
    -0.06
     Niet
    -0.06
    aba
    -0.06
    leo
    -0.06
    eyin
    -0.06
    POSITIVE LOGITS
    alsy
    0.07
    ungal
    0.06
    eldorf
    0.06
    ensch
    0.06
    chedulers
    0.06
    /providers
    0.06
    USES
    0.06
    /Dk
    0.06
    ëĨ
    0.06
    reviews
    0.06
    Activations Density 0.004%

    No Known Activations