© 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. 17-LLAMASCOPE-RES-131K
    11. 73649
    Prev
    Next
    INDEX
    Explanations

    themes related to fear and the impact of external pressures on individuals and societies

    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
    stÅĻÃŃ
    -0.07
    edelta
    -0.07
    aci
    -0.07
    Ïĩ
    -0.07
    kers
    -0.06
    RootElement
    -0.06
     Cros
    -0.06
    itorio
    -0.06
    Ø´Ùģ
    -0.06
    ponce
    -0.06
    POSITIVE LOGITS
     afraid
    0.10
     fear
    0.10
     Fear
    0.10
     fearful
    0.09
    Fear
    0.09
     terrified
    0.09
     hesitation
    0.09
     hes
    0.09
     kork
    0.08
     scared
    0.08
    Activations Density 0.081%

    No Known Activations