© 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. 9-LLAMASCOPE-RES-131K
    6. 95489
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to official processes and documentation

    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
    isel
    -0.07
    iced
    -0.06
    atÃŃm
    -0.06
    pto
    -0.06
     monarch
    -0.06
     Ø¢Ùħ
    -0.06
    Italic
    -0.06
    éri
    -0.06
    afd
    -0.06
    intl
    -0.06
    POSITIVE LOGITS
    PIO
    0.06
    opus
    0.06
    ipline
    0.06
     IllegalAccessException
    0.06
    ali
    0.06
    rence
    0.06
    -dat
    0.06
    ê¹
    0.06
     Opportunity
    0.06
    upert
    0.06
    Activations Density 0.014%

    No Known Activations