© 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. 27681
    Prev
    Next
    INDEX
    Explanations

    instances of knocking-related actions or events

    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
    ilim
    -0.07
    errer
    -0.07
     çĪ
    -0.07
    eprom
    -0.07
    getMock
    -0.07
    inki
    -0.07
    EPROM
    -0.07
    agli
    -0.07
    phia
    -0.07
    ossal
    -0.07
    POSITIVE LOGITS
     door
    0.15
     doors
    0.13
    Door
    0.11
     Door
    0.11
    -door
    0.11
    door
    0.10
    _door
    0.10
     двеÑĢ
    0.10
     Doors
    0.10
    éĸĢ
    0.09
    Activations Density 0.010%

    No Known Activations