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. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72610
    Prev
    Next
    INDEX
    Explanations

    references to music releases and albums

    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
    rop
    -0.07
    yw
    -0.06
    oble
    -0.06
    orr
    -0.06
    rrha
    -0.05
    ot
    -0.05
    irect
    -0.05
     Grove
    -0.05
     Cro
    -0.05
    br
    -0.05
    POSITIVE LOGITS
    assen
    0.08
    quette
    0.08
    olie
    0.07
    lias
    0.07
     Pett
    0.07
    .sav
    0.07
    ruh
    0.07
    Ïĥκ
    0.06
    etta
    0.06
    .Bounds
    0.06
    Activations Density 0.006%

    No Known Activations