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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5042
    Prev
    Next
    INDEX
    Explanations

    references to award selections and nominations

    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
    ibus
    -0.08
    nga
    -0.08
    onec
    -0.07
    ARRANT
    -0.07
    contri
    -0.07
    icari
    -0.07
    rlen
    -0.07
    ROLS
    -0.07
    ien
    -0.06
    Ñĩива
    -0.06
    POSITIVE LOGITS
     v
    0.07
    gather
    0.07
     selected
    0.06
    adu
    0.06
     pup
    0.06
    Marks
    0.06
     StreamWriter
    0.06
    .Win
    0.06
     zoekt
    0.06
    marks
    0.06
    Activations Density 0.041%

    No Known Activations