© 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. 118059
    Prev
    Next
    INDEX
    Explanations

    conditional statements and hypothetical scenarios

    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
    odule
    -0.07
    orts
    -0.06
    seau
    -0.06
    Å¡en
    -0.06
     Affero
    -0.06
    ega
    -0.06
    олов
    -0.06
    ardy
    -0.06
    acion
    -0.06
    лÑİб
    -0.06
    POSITIVE LOGITS
    rof
    0.08
    apur
    0.07
    ikat
    0.07
     told
    0.07
    alez
    0.07
    ä¸Ģç§į
    0.07
    otent
    0.06
    aeda
    0.06
    eros
    0.06
     Walt
    0.06
    Activations Density 0.006%

    No Known Activations