© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 86750
    Prev
    Next
    INDEX
    Explanations

    terms related to social impact and rights issues

    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
    oader
    -0.06
     Rouge
    -0.06
    ůvod
    -0.06
     *__
    -0.06
     Failed
    -0.06
    Æ
    -0.06
    alchemy
    -0.06
    idge
    -0.06
    icer
    -0.06
    ats
    -0.06
    POSITIVE LOGITS
     interests
    0.08
    eker
    0.07
     interest
    0.07
    ãĤ¤ãĤ¯
    0.07
    inesis
    0.07
    .tc
    0.06
     directly
    0.06
    baugh
    0.06
     daily
    0.06
    OutOfBounds
    0.06
    Activations Density 0.015%

    No Known Activations