Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44375
    Prev
    Next
    INDEX
    Explanations

    references to copyright 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
    ãĤ¦ãĥ³
    -0.07
    ktop
    -0.06
    getManager
    -0.06
     Pazar
    -0.06
    wich
    -0.06
    cbc
    -0.06
     Bucc
    -0.06
    äºŃ
    -0.06
    è©©
    -0.06
    OLEAN
    -0.06
    POSITIVE LOGITS
     ©
    0.12
     Contributors
    0.10
    (c
    0.10
     (
    0.09
     IBM
    0.09
     contributors
    0.08
     Amazon
    0.08
    ©
    0.08
    (C
    0.08
     LGPL
    0.07
    Activations Density 0.005%

    No Known Activations