© 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. 127309
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location or area

    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
    uber
    -0.07
    fait
    -0.07
    efs
    -0.07
    efon
    -0.07
    eway
    -0.07
    dÄĽl
    -0.07
    ละ
    -0.07
    mith
    -0.06
    yal
    -0.06
    ovanou
    -0.06
    POSITIVE LOGITS
    sWith
    0.07
    swith
    0.07
    ras
    0.06
     Exped
    0.06
    ings
    0.06
    лиÑĪком
    0.06
    Dash
    0.06
     Elaine
    0.06
    们
    0.06
    ship
    0.05
    Activations Density 0.000%

    No Known Activations