© 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. 16834
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface design and interaction components

    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
    UBL
    -0.07
    æĿ¡
    -0.07
     laps
    -0.07
     меÑĢ
    -0.06
    dbg
    -0.06
    olin
    -0.06
    ']->
    -0.06
    wall
    -0.06
    ampo
    -0.06
    trees
    -0.06
    POSITIVE LOGITS
    orf
    0.08
    ackers
    0.06
    ycastle
    0.06
    kowski
    0.06
    -circle
    0.06
    .toolbox
    0.06
    engo
    0.06
    ico
    0.06
    oup
    0.06
    oyer
    0.06
    Activations Density 0.010%

    No Known Activations