© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90053
    Prev
    Next
    INDEX
    Explanations

    concepts related to geographic boundaries and location details

    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
    izia
    -0.07
    imeline
    -0.07
    isma
    -0.07
    timeline
    -0.07
    _TestCase
    -0.07
    isel
    -0.07
     Sabb
    -0.07
    aggi
    -0.06
    534
    -0.06
    mozilla
    -0.06
    POSITIVE LOGITS
     centroid
    0.07
     actual
    0.06
     centroids
    0.06
    UGE
    0.06
     bulk
    0.06
     street
    0.06
     Finn
    0.06
    quez
    0.06
     precision
    0.05
    _defs
    0.05
    Activations Density 0.001%

    No Known Activations