© 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. 70845
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to interpersonal relationships and experiences

    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
    ãĤĦãĤĭ
    -0.07
    adden
    -0.07
    ãĤĴè¦ĭãĤĭ
    -0.07
     ç«
    -0.07
    ertz
    -0.07
    ãģ¤ãģij
    -0.07
    CRY
    -0.07
    aub
    -0.06
    ازÛĮ
    -0.06
    FINITE
    -0.06
    POSITIVE LOGITS
     probably
    0.14
     maybe
    0.13
     yourself
    0.13
     your
    0.13
     perhaps
    0.12
     yourselves
    0.11
    your
    0.11
     vielleicht
    0.11
     Probably
    0.11
    maybe
    0.10
    Activations Density 0.035%

    No Known Activations