© 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. 77327
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics

    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
    uber
    -0.08
     addCriterion
    -0.07
     fres
    -0.07
    ampus
    -0.06
     ydk
    -0.06
    ãĥ³ãĥij
    -0.06
    oise
    -0.06
    .appspot
    -0.06
     Cly
    -0.06
    ache
    -0.06
    POSITIVE LOGITS
    áb
    0.07
    ennen
    0.07
    erez
    0.06
     Bust
    0.06
    ogan
    0.06
    uras
    0.06
    itra
    0.06
    fik
    0.06
    adesh
    0.06
    SetName
    0.06
    Activations Density 0.044%

    No Known Activations