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. 44267
    Prev
    Next
    INDEX
    Explanations

    constructs related to personal insight and understanding in the context of performance

    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
     extensively
    -0.06
     only
    -0.06
     segunda
    -0.05
     fourth
    -0.05
     exclusively
    -0.05
    third
    -0.05
     annually
    -0.05
    ">//
    -0.05
    second
    -0.05
     busiest
    -0.05
    POSITIVE LOGITS
     given
    0.13
     thing
    0.13
     item
    0.12
     piece
    0.11
     particular
    0.11
     chosen
    0.11
     object
    0.10
    given
    0.10
     material
    0.10
     subject
    0.10
    Activations Density 0.131%

    No Known Activations