© 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 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. 106257
    Prev
    Next
    INDEX
    Explanations

    references to specific conditions or situations that impact well-being

    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
    utin
    -0.07
     Lust
    -0.06
    ãĥ³ãĥĨ
    -0.06
    BAB
    -0.06
    bab
    -0.06
     tomorrow
    -0.06
     Gem
    -0.06
    ATAB
    -0.05
    atab
    -0.05
    кÑĥ
    -0.05
    POSITIVE LOGITS
    421
    0.09
    çĿ
    0.07
    422
    0.07
    ÙĪØŃ
    0.07
    neys
    0.07
    467
    0.07
    _$_
    0.06
    lej
    0.06
    presence
    0.06
    ุม
    0.06
    Activations Density 0.000%

    No Known Activations