© 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. 117228
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and authors

    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
    ollo
    -0.07
    ugo
    -0.06
     bells
    -0.06
     Schro
    -0.06
    urities
    -0.06
    оÑĢоз
    -0.06
    ÛĮØ´
    -0.06
    airro
    -0.06
    ansi
    -0.06
    cus
    -0.06
    POSITIVE LOGITS
    veis
    0.06
    GAN
    0.06
    .au
    0.06
    iled
    0.06
     Jr
    0.06
    uned
    0.06
    /goto
    0.06
    ÑĢеÑģ
    0.06
    _vc
    0.06
     Team
    0.06
    Activations Density 0.012%

    No Known Activations