© 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. 95015
    Prev
    Next
    INDEX
    Explanations

    instances of persuasive language or arguments

    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
    rika
    -0.07
    afen
    -0.07
    Ùijا
    -0.07
    tt
    -0.07
    ế
    -0.07
    ãĥªãĤ¢
    -0.06
    .tt
    -0.06
    mtx
    -0.06
    _LS
    -0.06
    ckt
    -0.06
    POSITIVE LOGITS
     an
    0.06
    egal
    0.06
    igan
    0.05
    stral
    0.05
    /cgi
    0.05
    lak
    0.05
    imb
    0.05
     hers
    0.05
    IPP
    0.05
    esan
    0.05
    Activations Density 0.001%

    No Known Activations