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. 22-LLAMASCOPE-RES-131K
    6. 5767
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing quantity or degree, particularly the use of the word "quite" or variations of "a"

    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
     very
    -0.06
     somewhat
    -0.06
    qv
    -0.06
    mer
    -0.06
     kinds
    -0.06
    ruc
    -0.06
    ase
    -0.06
     only
    -0.06
     Bulk
    -0.05
    ç§į
    -0.05
    POSITIVE LOGITS
    -ÑĤаки
    0.10
     amount
    0.08
    LBL
    0.07
    amount
    0.07
    DownList
    0.07
    вай
    0.07
    oker
    0.07
     Ñģебе
    0.07
    ude
    0.07
    atta
    0.07
    Activations Density 0.004%

    No Known Activations