© 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. 97488
    Prev
    Next
    INDEX
    Explanations

    references to collaborative efforts and resources in a community context

    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
    tha
    -0.07
    mana
    -0.06
    eres
    -0.06
    wagon
    -0.06
    eed
    -0.06
    lio
    -0.06
    bah
    -0.05
    etti
    -0.05
    erase
    -0.05
    boro
    -0.05
    POSITIVE LOGITS
    ä¾
    0.08
    kaar
    0.07
    ossed
    0.07
     ëĭ¹
    0.07
    dish
    0.07
    аÑĤаÑĢ
    0.07
    mlink
    0.07
     Kendall
    0.07
    Ñīий
    0.07
    ÄĻk
    0.06
    Activations Density 0.004%

    No Known Activations