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. 43637
    Prev
    Next
    INDEX
    Explanations

    references to technology companies and their market dynamics

    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
    ooter
    -0.06
     ÑĢиз
    -0.05
    ãĥĩãĥ«
    -0.05
    ADF
    -0.05
    .Helpers
    -0.05
    ìĭľìĺ¤
    -0.05
    andez
    -0.05
    rouw
    -0.05
    rix
    -0.05
    ivable
    -0.05
    POSITIVE LOGITS
     dominate
    0.21
     domination
    0.20
     dominance
    0.20
     dominates
    0.20
     rule
    0.19
     dominating
    0.19
     dominated
    0.18
     monopol
    0.18
     domina
    0.17
     ruled
    0.17
    Activations Density 0.126%

    No Known Activations