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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94703
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disillusionment or skepticism towards societal expectations and 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
    Ìī
    -0.07
    ç§
    -0.07
    Compound
    -0.07
    acket
    -0.07
    /download
    -0.07
    è¡Ľ
    -0.07
    erb
    -0.06
    ahat
    -0.06
     Compound
    -0.06
    çĸ
    -0.06
    POSITIVE LOGITS
     Marvin
    0.07
    کر
    0.06
     вз
    0.06
    enheim
    0.06
    ullah
    0.05
    DoubleClick
    0.05
     ostat
    0.05
    ncy
    0.05
    Animated
    0.05
     Gron
    0.05
    Activations Density 0.022%

    No Known Activations