© 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. 9-LLAMASCOPE-RES-131K
    11. 97942
    Prev
    Next
    INDEX
    Explanations

    the word "update" and its associated variations indicating changes or announcements

    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
    ignet
    -0.07
    обÑĢаз
    -0.06
    ÑģÑĤва
    -0.06
    vana
    -0.06
    dep
    -0.06
    stagram
    -0.06
    aca
    -0.06
    igma
    -0.06
    posta
    -0.06
    adoo
    -0.05
    POSITIVE LOGITS
     dikke
    0.07
     actionTypes
    0.07
    375
    0.06
    ableView
    0.06
    emic
    0.06
    Viewport
    0.06
     quar
    0.06
    utut
    0.06
    Nano
    0.06
    enes
    0.06
    Activations Density 0.005%

    No Known Activations