© 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. 127677
    Prev
    Next
    INDEX
    Explanations

    phrases questioning knowledge or awareness

    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
     even
    -0.07
     nowhere
    -0.07
     anyone
    -0.07
     any
    -0.06
    Ñĥжд
    -0.06
     if
    -0.06
    yster
    -0.06
    statusCode
    -0.06
     anywhere
    -0.06
     guy
    -0.05
    POSITIVE LOGITS
    essler
    0.07
    icode
    0.07
    CHED
    0.07
    bakan
    0.07
    bek
    0.07
     plu
    0.07
    _RB
    0.07
    iar
    0.07
    bows
    0.07
    arious
    0.06
    Activations Density 0.007%

    No Known Activations