© 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. 9-LLAMASCOPE-RES-131K
    6. 95144
    Prev
    Next
    INDEX
    Explanations

    instances of emotional conflict and personal realization

    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
    bau
    -0.06
     substance
    -0.06
    ümü
    -0.06
    ioni
    -0.06
     yourselves
    -0.06
    Locker
    -0.06
    chs
    -0.06
     unc
    -0.06
    è¾ŀ
    -0.06
    oun
    -0.06
    POSITIVE LOGITS
    PointerException
    0.07
    iffies
    0.07
     christmas
    0.06
    ialized
    0.06
    iban
    0.06
    (gcf
    0.06
    ayne
    0.06
    ä»¶
    0.06
    _SESSION
    0.06
    getPosition
    0.06
    Activations Density 0.072%

    No Known Activations