© 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. 86181
    Prev
    Next
    INDEX
    Explanations

    instances of challenging or adverse conditions related to the environment or travel

    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
    held
    -0.06
     Drop
    -0.05
     anch
    -0.05
    anch
    -0.05
     positioning
    -0.05
     stray
    -0.05
     recursion
    -0.05
     ReturnValue
    -0.05
    anning
    -0.05
     participant
    -0.05
    POSITIVE LOGITS
    è¸
    0.08
    Ñıми
    0.08
    į°ìĿ´
    0.08
    éĭ
    0.08
    å±¥
    0.08
    essian
    0.07
    _mD
    0.07
    osg
    0.07
    quet
    0.07
     Moist
    0.07
    Activations Density 0.023%

    No Known Activations