© 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. 94105
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to sports 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
     Feinstein
    -0.06
    icons
    -0.06
    odox
    -0.06
     holy
    -0.06
     wa
    -0.06
    olis
    -0.06
     shout
    -0.05
    .defaults
    -0.05
     quantity
    -0.05
    uzu
    -0.05
    POSITIVE LOGITS
    ationToken
    0.09
    à¹Ĥà¸ģ
    0.07
    .Ui
    0.07
    à¹ģรà¸ģ
    0.07
    .scalablytyped
    0.07
    922
    0.07
    nger
    0.07
    Gratis
    0.07
    -degree
    0.07
    .toByteArray
    0.07
    Activations Density 0.033%

    No Known Activations