© 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. 57132
    Prev
    Next
    INDEX
    Explanations

    assertions of capability or validity regarding talent, ability, or beliefs

    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
    ilde
    -0.08
    ieber
    -0.07
    TEL
    -0.07
    nul
    -0.07
    ilia
    -0.07
    aeda
    -0.07
     tod
    -0.07
    ýn
    -0.07
    rido
    -0.06
    ndern
    -0.06
    POSITIVE LOGITS
     ÙĪØ£ÙĨ
    0.09
    askell
    0.08
    enaire
    0.07
    ãĤ¿ãĥ¼
    0.06
     bindActionCreators
    0.06
    галÑĸ
    0.06
     Mirage
    0.06
    enburg
    0.06
    ena
    0.06
    /is
    0.06
    Activations Density 0.056%

    No Known Activations