© 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. 60475
    Prev
    Next
    INDEX
    Explanations

    negative outcomes and consequences of personal failure or societal events

    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
    errupted
    -0.07
    нин
    -0.07
    leck
    -0.07
    vecs
    -0.07
    à¸ģà¸ķ
    -0.07
     leaps
    -0.07
     doom
    -0.07
    lek
    -0.07
    ognito
    -0.07
    ifen
    -0.07
    POSITIVE LOGITS
     reality
    0.09
     real
    0.09
    Reality
    0.09
    real
    0.08
     suddenly
    0.08
     Reality
    0.08
     Real
    0.08
    Real
    0.07
     REAL
    0.07
     realization
    0.07
    Activations Density 0.036%

    No Known Activations