© 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. 93148
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or varying degrees of agreement

    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
    isplay
    -0.07
    ãĤ¤ãĤº
    -0.06
    ani
    -0.06
    517
    -0.06
    ultipart
    -0.06
    onda
    -0.06
    uler
    -0.06
    abad
    -0.06
    ovah
    -0.06
    altet
    -0.06
    POSITIVE LOGITS
     extent
    0.17
    extent
    0.14
     extents
    0.11
     degree
    0.10
    .extent
    0.10
     tune
    0.09
    Extent
    0.09
    _extent
    0.09
    ç¨ĭ度
    0.08
    degree
    0.08
    Activations Density 0.049%

    No Known Activations