© 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. 86587
    Prev
    Next
    INDEX
    Explanations

    expressions related to direct communication and appeals, particularly regarding arrangements or requests

    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
    ã
    -0.06
     Sabha
    -0.06
    IRO
    -0.06
    uzzi
    -0.06
    InBackground
    -0.06
    wyn
    -0.06
    wind
    -0.06
    ãĥªãĤ«
    -0.06
    stÃŃ
    -0.06
    illus
    -0.06
    POSITIVE LOGITS
     directly
    0.40
     direct
    0.38
    direct
    0.34
    缴æİ¥
    0.32
     Direct
    0.31
    Direct
    0.31
     DIRECT
    0.28
     diret
    0.26
    -direct
    0.26
    _direct
    0.26
    Activations Density 0.078%

    No Known Activations