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. 43994
    Prev
    Next
    INDEX
    Explanations

    specific visual elements or branding terms in the text

    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
    awai
    -0.08
    erland
    -0.06
    iola
    -0.06
    NM
    -0.05
    är
    -0.05
    ollo
    -0.05
     NM
    -0.05
     MMI
    -0.05
    ikel
    -0.05
    ünd
    -0.05
    POSITIVE LOGITS
     signage
    0.11
     City
    0.11
     city
    0.10
     signs
    0.10
     sign
    0.10
     street
    0.10
     Signs
    0.10
     Streets
    0.10
     residents
    0.09
    City
    0.09
    Activations Density 0.002%

    No Known Activations