© 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. 78466
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a search or desire for something

    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
    Enlarge
    -0.06
    äºĭ
    -0.06
    âĢ¡
    -0.06
     Leban
    -0.06
     Byl
    -0.06
    _lite
    -0.06
    ossip
    -0.05
    erson
    -0.05
    _large
    -0.05
    oko
    -0.05
    POSITIVE LOGITS
    APS
    0.07
    нина
    0.07
    omu
    0.07
    _parms
    0.07
     Volunteers
    0.07
     recruits
    0.06
    -caret
    0.06
    ¼
    0.06
    erli
    0.06
    erd
    0.06
    Activations Density 0.005%

    No Known Activations