© 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. 55060
    Prev
    Next
    INDEX
    Explanations

    expressions related to issues of concern and ethical dilemmas

    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
    zac
    -0.08
    à¸Ļ
    -0.08
    iggers
    -0.07
    د
    -0.07
    ãģĦãĤĭ
    -0.07
    sters
    -0.07
    ulse
    -0.06
    uras
    -0.06
    ians
    -0.06
    dk
    -0.06
    POSITIVE LOGITS
    lessly
    0.11
    ingly
    0.10
    ment
    0.09
    ÑģÑı
    0.09
    fully
    0.08
     matters
    0.08
    738
    0.07
    vä
    0.07
    wart
    0.07
    ½æķ°
    0.07
    Activations Density 0.010%

    No Known Activations