© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57589
    Prev
    Next
    INDEX
    Explanations

    numerical data or values associated with costs and measurements

    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
    Ģ
    -0.07
     prostitut
    -0.07
     toItem
    -0.07
     prostituer
    -0.07
    agh
    -0.07
    WXYZ
    -0.07
    šov
    -0.07
    DonaldTrump
    -0.07
     Angiosper
    -0.07
    raud
    -0.06
    POSITIVE LOGITS
    nga
    0.08
    anse
    0.07
    802
    0.06
    ovi
    0.06
    jab
    0.06
    i
    0.06
    'i
    0.06
    Question
    0.06
    illard
    0.06
     dr
    0.06
    Activations Density 0.000%

    No Known Activations