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. 22-LLAMASCOPE-RES-131K
    6. 5590
    Prev
    Next
    INDEX
    Explanations

    concepts that are theoretical or not yet realized

    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
    oward
    -0.06
     Noticed
    -0.05
     Paz
    -0.05
    OKIE
    -0.05
    tle
    -0.05
    htar
    -0.05
    astos
    -0.05
     mainstream
    -0.05
    dg
    -0.05
    156
    -0.05
    POSITIVE LOGITS
    idea
    0.11
    concept
    0.11
     Concept
    0.10
     idea
    0.10
     conceptual
    0.10
    纸
    0.10
     concept
    0.10
     conception
    0.10
    Concept
    0.10
     Idea
    0.10
    Activations Density 0.026%

    No Known Activations