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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55288
    Prev
    Next
    INDEX
    Explanations

    locations and names of geographical places, particularly towns and landmarks

    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
    river
    -0.07
    antz
    -0.07
    Metro
    -0.06
    River
    -0.06
     Metro
    -0.06
     strikes
    -0.06
    metro
    -0.06
    akers
    -0.06
    reet
    -0.06
    anny
    -0.06
    POSITIVE LOGITS
    ieber
    0.09
     Resort
    0.09
     resort
    0.08
    azzo
    0.08
    -minus
    0.08
     resorts
    0.07
     turist
    0.07
    olu
    0.07
    ÙĪØ§
    0.07
     village
    0.07
    Activations Density 0.049%

    No Known Activations