© 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. 73700
    Prev
    Next
    INDEX
    Explanations

    the name "Hans" in various contexts

    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
    voke
    -0.07
    ADIO
    -0.07
    æģ
    -0.07
    /umd
    -0.07
    ptrdiff
    -0.07
    lec
    -0.07
    adlo
    -0.07
    _ABI
    -0.07
    tees
    -0.07
    uncated
    -0.07
    POSITIVE LOGITS
    rav
    0.07
    angu
    0.07
     disc
    0.07
    sam
    0.07
    emo
    0.06
    ãĥ¬ãĥ¼
    0.06
    sip
    0.06
    itory
    0.06
    ¼
    0.06
    sing
    0.06
    Activations Density 0.003%

    No Known Activations