© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56959
    Prev
    Next
    INDEX
    Explanations

    keywords related to roles and responsibilities in specific contexts

    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
    aris
    -0.07
     actionTypes
    -0.07
     setting
    -0.06
     surrounding
    -0.06
    itter
    -0.06
     surround
    -0.06
     surrounds
    -0.06
     ActionTypes
    -0.06
    _UNIX
    -0.06
     whats
    -0.06
    POSITIVE LOGITS
    们
    0.12
     nÃło
    0.11
    åĢij
    0.10
    (s
    0.10
    sto
    0.09
    sthrough
    0.09
    closest
    0.08
     closest
    0.08
     thứ
    0.08
    sex
    0.08
    Activations Density 0.253%

    No Known Activations