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. 11432
    Prev
    Next
    INDEX
    Explanations

    references to medical studies and their findings

    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
    iones
    -0.08
    ller
    -0.08
    eton
    -0.08
    ProgressHUD
    -0.08
    anker
    -0.08
    pollo
    -0.07
    .Wrap
    -0.07
     Wak
    -0.07
    latin
    -0.07
    cuador
    -0.07
    POSITIVE LOGITS
     Lisbon
    0.14
     Portugal
    0.13
     Aç
    0.12
    .pt
    0.11
     Portug
    0.11
     Portuguese
    0.11
     Lis
    0.11
     RTP
    0.10
    èij¡
    0.09
     Sous
    0.09
    Activations Density 0.098%

    No Known Activations