© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 15654
    Prev
    Next
    INDEX
    Explanations

    phrases indicating cognitive confusion or a state of being overwhelmed

    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
    /stdc
    -0.06
    ANDLE
    -0.06
    832
    -0.06
     doubly
    -0.06
    ACHI
    -0.06
     cellspacing
    -0.06
    acket
    -0.06
    andal
    -0.06
     combos
    -0.05
    rove
    -0.05
    POSITIVE LOGITS
    èĶµ
    0.07
    ÑĮко
    0.07
    ãĢ
    0.07
    нÑĮ
    0.07
    oti
    0.07
    leftright
    0.07
    ÑĤин
    0.07
    stal
    0.06
    |#
    0.06
    oje
    0.06
    Activations Density 0.000%

    No Known Activations