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. 43469
    Prev
    Next
    INDEX
    Explanations

    actions and activities related to physical movement or bodily functions

    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
    astes
    -0.07
    .xtext
    -0.07
    ãĥ¼ãĥģ
    -0.07
    ê±´
    -0.07
    ernals
    -0.07
    isans
    -0.07
     assistir
    -0.07
    ekler
    -0.07
     suche
    -0.07
    änge
    -0.07
    POSITIVE LOGITS
     peoples
    0.07
     and
    0.07
     furniture
    0.07
     imaginary
    0.07
     chairs
    0.07
     ourselves
    0.07
     themselves
    0.06
     people
    0.06
     quarters
    0.06
     himself
    0.06
    Activations Density 0.097%

    No Known Activations