© 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. 40615
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thought" and its variations, indicating reflective or contemplative statements

    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
    sov
    -0.07
    ped
    -0.07
    érc
    -0.07
    abaj
    -0.07
    権
    -0.07
    ¯
    -0.06
    ederland
    -0.06
    /sources
    -0.06
    ascimento
    -0.06
    loven
    -0.06
    POSITIVE LOGITS
    fully
    0.09
     surely
    0.07
    lessly
    0.07
     sobie
    0.07
     patter
    0.07
    _CONTINUE
    0.06
    -about
    0.06
    fulness
    0.06
    maybe
    0.06
    mere
    0.06
    Activations Density 0.012%

    No Known Activations