© 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. 30446
    Prev
    Next
    INDEX
    Explanations

    terms related to coercion or pressure, particularly in a context of forceful actions or obligations

    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
    kish
    -0.07
    enders
    -0.06
    .testng
    -0.06
    671
    -0.06
    ãĥ³ãĥij
    -0.06
    ilen
    -0.06
    å¤ķ
    -0.06
     excell
    -0.06
    ipp
    -0.06
    .sd
    -0.06
    POSITIVE LOGITS
    ara
    0.07
    LOY
    0.06
    thenReturn
    0.06
     Arbitrary
    0.06
    thren
    0.06
    emo
    0.06
    uh
    0.06
    é¡»
    0.06
    ta
    0.06
     Criteria
    0.06
    Activations Density 0.039%

    No Known Activations