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. 43434
    Prev
    Next
    INDEX
    Explanations

    mentions of book awards and publication statuses

    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
    QRS
    -0.07
    ibraltar
    -0.06
     datings
    -0.06
    iable
    -0.06
    prung
    -0.06
    storybook
    -0.06
    itre
    -0.06
    βολ
    -0.06
    edy
    -0.06
    Ĭ
    -0.06
    POSITIVE LOGITS
     option
    0.15
    option
    0.12
    -option
    0.11
     Option
    0.11
     runner
    0.10
    Option
    0.10
     OPTION
    0.10
     rep
    0.10
     translated
    0.09
     favor
    0.09
    Activations Density 0.026%

    No Known Activations