© 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. 28084
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and related contextual identifiers

    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
    veh
    -0.07
    Ñıн
    -0.07
    uters
    -0.07
    ÑĥÑĢн
    -0.07
    imensional
    -0.06
    nonnull
    -0.06
    resco
    -0.06
    weed
    -0.06
    wie
    -0.06
    амп
    -0.06
    POSITIVE LOGITS
     ph
    0.06
     Jew
    0.05
    Playback
    0.05
    ç´
    0.05
    taj
    0.05
    åĭ¢
    0.05
     ris
    0.05
    asure
    0.05
     Ø´Ùħ
    0.05
     physically
    0.05
    Activations Density 0.001%

    No Known Activations