© 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. 104656
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations and administrative 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
    кÑĸн
    -0.07
    )NULL
    -0.07
    wind
    -0.06
    etest
    -0.06
    ода
    -0.06
    themes
    -0.06
    avad
    -0.06
    apesh
    -0.06
    baz
    -0.06
    .repeat
    -0.06
    POSITIVE LOGITS
    mn
    0.08
    auer
    0.06
    erli
    0.06
    ialog
    0.06
    onest
    0.06
     Skull
    0.06
    onian
    0.06
    icion
    0.06
     Nicholson
    0.06
     Strings
    0.06
    Activations Density 0.003%

    No Known Activations