© 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. 117011
    Prev
    Next
    INDEX
    Explanations

    specific names or labels associated with types of organisms or species

    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
    oup
    -0.08
     of
    -0.07
    of
    -0.06
     av
    -0.06
    ist
    -0.06
     medic
    -0.06
     pg
    -0.06
    ikip
    -0.06
    nes
    -0.06
    aniem
    -0.06
    POSITIVE LOGITS
    indrome
    0.07
    .mybatisplus
    0.07
    duk
    0.07
    #
    0.07
    LinkId
    0.07
    .MockMvc
    0.07
    éºĹ
    0.07
     вÑĸдноÑģ
    0.06
    DataExchange
    0.06
    .synthetic
    0.06
    Activations Density 0.000%

    No Known Activations