© 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 EvalsExportsAPI 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. 82942
    Prev
    Next
    INDEX
    Explanations

    references to locations or positions in geographical contexts

    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
    ãĥĽ
    -0.07
    ç£
    -0.07
    Nos
    -0.06
    /sn
    -0.06
    agar
    -0.06
    ouv
    -0.06
    oble
    -0.06
    OTS
    -0.06
    mts
    -0.06
     treff
    -0.06
    POSITIVE LOGITS
    avatel
    0.07
    ĵ
    0.07
    yo
    0.06
    ungs
    0.06
    yling
    0.06
    367
    0.06
    amps
    0.06
    estli
    0.06
    emale
    0.06
    ibel
    0.06
    Activations Density 0.020%

    No Known Activations