© 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 EvalsExportsinterp-engineNEWAPI 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. 81181
    Prev
    Next
    INDEX
    Explanations

    instances of the reflexive pronoun "sich" and related grammatical structures

    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
    allery
    -0.07
     se
    -0.07
    lun
    -0.07
    ä»»
    -0.07
     Sheldon
    -0.07
     fl
    -0.06
    yon
    -0.06
    RCT
    -0.06
    TRL
    -0.06
     min
    -0.06
    POSITIVE LOGITS
     udál
    0.09
    ps
    0.07
    246
    0.07
    542
    0.06
     purs
    0.06
    yles
    0.06
    iller
    0.06
     McD
    0.06
    aries
    0.06
    aze
    0.06
    Activations Density 0.016%

    No Known Activations