© 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. 3439
    Prev
    Next
    INDEX
    Explanations

    HTML buttons and their various attributes

    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
     gratuites
    -0.08
    gili
    -0.07
    ILON
    -0.07
    uten
    -0.07
    ogn
    -0.06
    utral
    -0.06
    rouch
    -0.06
    utut
    -0.06
    ekte
    -0.06
    yar
    -0.06
    POSITIVE LOGITS
     Ritch
    0.06
     Kas
    0.06
    enas
    0.06
    à¥ĭà¤ļ
    0.06
    unner
    0.06
     Royal
    0.06
    \grid
    0.05
     ÙĦÙĩا
    0.05
     DCHECK
    0.05
     conform
    0.05
    Activations Density 0.002%

    No Known Activations