© 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. 17706
    Prev
    Next
    INDEX
    Explanations

    names mentioned in a document, particularly last names

    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
    er
    -0.09
    tight
    -0.08
    erap
    -0.07
    ging
    -0.07
    صاÙĦ
    -0.07
    ç±į
    -0.07
    spot
    -0.07
    illac
    -0.07
     Boeh
    -0.07
    erdale
    -0.07
    POSITIVE LOGITS
    ius
    0.10
    heimer
    0.08
    nd
    0.08
    -vous
    0.07
    'gc
    0.07
    hower
    0.07
    heim
    0.07
    oids
    0.07
    ities
    0.07
    witter
    0.07
    Activations Density 0.015%

    No Known Activations