© 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. 72166
    Prev
    Next
    INDEX
    Explanations

    proper nouns that refer to geographic locations or regions

    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
    utow
    -0.07
    scar
    -0.07
    ifer
    -0.07
    sworth
    -0.07
    cad
    -0.06
    arius
    -0.06
    rary
    -0.06
    vig
    -0.06
     Hut
    -0.06
    omer
    -0.06
    POSITIVE LOGITS
    anging
    0.08
    quina
    0.08
    most
    0.07
    lest
    0.07
    atsby
    0.07
    UMB
    0.07
    ties
    0.06
    ThanOr
    0.06
    preci
    0.06
    dad
    0.06
    Activations Density 0.005%

    No Known Activations