© 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. 17941
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons and causation

    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
    esModule
    -0.07
    Æ¡
    -0.07
    means
    -0.07
    ноÑģи
    -0.06
    .getSeconds
    -0.06
    otime
    -0.06
    initely
    -0.06
    åħ¸
    -0.06
    meaning
    -0.06
     neighb
    -0.06
    POSITIVE LOGITS
     success
    0.10
     increase
    0.08
    success
    0.07
     successful
    0.07
     Success
    0.07
     increased
    0.07
     successes
    0.07
     seemingly
    0.07
    uter
    0.07
     observed
    0.07
    Activations Density 0.035%

    No Known Activations