© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103990
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and environments

    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
    ôn
    -0.07
    :animated
    -0.07
    .scalablytyped
    -0.07
    .GridView
    -0.06
    714
    -0.06
    illet
    -0.06
     Pratt
    -0.06
    urr
    -0.06
     Dynasty
    -0.06
    çīĮ
    -0.06
    POSITIVE LOGITS
     باÙĦا
    0.07
    appa
    0.07
    mine
    0.07
    edu
    0.07
    ãĥĽ
    0.06
    chy
    0.06
    reo
    0.06
    stan
    0.06
    åºľ
    0.06
    овиÑĩ
    0.06
    Activations Density 0.017%

    No Known Activations