© 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. 17-LLAMASCOPE-RES-131K
    11. 119631
    Prev
    Next
    INDEX
    Explanations

    references to copyright information and years

    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
    bie
    -0.06
     alone
    -0.06
    201
    -0.05
    oby
    -0.05
     coordinates
    -0.05
    eed
    -0.05
    ira
    -0.05
    cha
    -0.05
    l
    -0.05
     forg
    -0.05
    POSITIVE LOGITS
    ÅĻes
    0.08
    _codegen
    0.08
    ibold
    0.08
     ÑģлÑĥÑħ
    0.08
    mrt
    0.07
    .scalablytyped
    0.07
    \Migrations
    0.07
    agements
    0.07
    erli
    0.07
    ovÃŃ
    0.07
    Activations Density 0.001%

    No Known Activations