© 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. 27757
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and performances

    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
    ses
    -0.13
    /or
    -0.10
    /her
    -0.09
    standing
    -0.08
    stantiate
    -0.08
    duct
    -0.07
    ductive
    -0.07
    ÏĦεÏģ
    -0.07
    cribe
    -0.07
    аÑģ
    -0.07
    POSITIVE LOGITS
    orem
    0.16
    notated
    0.12
    oretical
    0.10
    ories
    0.10
    olated
    0.10
    /OR
    0.09
    grily
    0.09
    semble
    0.08
    ynchronously
    0.08
    naments
    0.08
    Activations Density 0.183%

    No Known Activations