© 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. 57040
    Prev
    Next
    INDEX
    Explanations

    phrases characterized by simplicity or clarity

    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
    kop
    -0.07
    otron
    -0.06
    fang
    -0.06
    atoon
    -0.06
    apis
    -0.06
    InputDialog
    -0.06
    achu
    -0.06
    agoon
    -0.06
    tte
    -0.06
    neys
    -0.06
    POSITIVE LOGITS
     setFrame
    0.07
    ï¸ı
    0.07
    -simple
    0.07
    FilterWhere
    0.07
     gig
    0.07
    ifdef
    0.06
    .Script
    0.06
    ãĥĭãĤ¢
    0.06
     setObject
    0.06
    228
    0.06
    Activations Density 0.006%

    No Known Activations