© 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. 17718
    Prev
    Next
    INDEX
    Explanations

    specific time stamps or time-related information

    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
     Dah
    -0.07
    Ĥæķ°
    -0.07
    оÑĦ
    -0.07
     tabIndex
    -0.06
     ztr
    -0.06
    inne
    -0.06
    gard
    -0.06
    edy
    -0.06
     Far
    -0.06
    ypi
    -0.06
    POSITIVE LOGITS
    adius
    0.07
    PIC
    0.07
    (Collision
    0.07
    èĦ
    0.06
     اذ
    0.06
    FileSync
    0.06
    magnitude
    0.06
    WXYZ
    0.06
    436
    0.06
    wechat
    0.06
    Activations Density 0.005%

    No Known Activations