© 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. 5122
    Prev
    Next
    INDEX
    Explanations

    discussions about the human experience and condition

    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
    eka
    -0.07
    uzzi
    -0.07
    oken
    -0.07
    uz
    -0.07
    obraz
    -0.07
    ạp
    -0.06
    LEN
    -0.06
    atching
    -0.06
     Folk
    -0.06
    ÑĮми
    -0.06
    POSITIVE LOGITS
     human
    0.12
    human
    0.10
    -human
    0.09
     Human
    0.09
    Human
    0.08
     humans
    0.08
    _human
    0.07
     humano
    0.07
     hum
    0.07
     humanity
    0.07
    Activations Density 0.057%

    No Known Activations