© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 17115
    Prev
    Next
    INDEX
    Explanations

    descriptive language focused on historical and cultural 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
     Dün
    -0.10
     tô
    -0.07
     æ¼
    -0.07
    Ñħи
    -0.07
    discard
    -0.07
    iry
    -0.07
    Ấ
    -0.07
     indust
    -0.07
     Ãľst
    -0.07
     dün
    -0.07
    POSITIVE LOGITS
     fountain
    0.07
     pavement
    0.07
     benches
    0.06
    ãĥ¼ãĥł
    0.06
     colon
    0.06
     civic
    0.06
     fronts
    0.06
     pedestrian
    0.06
     pedest
    0.06
     sidewalk
    0.06
    Activations Density 0.008%

    No Known Activations