© 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. 15-LLAMASCOPE-RES-131K
    11. 62397
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and events in Manhattan

    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
    ya
    -0.06
    Oregon
    -0.06
     Rams
    -0.06
     Oregon
    -0.06
    yles
    -0.06
    imos
    -0.06
    èĥ¡
    -0.06
     Portland
    -0.06
     Roberts
    -0.06
    618
    -0.06
    POSITIVE LOGITS
    NY
    0.15
     NYC
    0.15
     NY
    0.14
     Brooklyn
    0.11
    .ny
    0.10
     NYPD
    0.10
     Manhattan
    0.09
     New
    0.09
     Bronx
    0.09
    New
    0.09
    Activations Density 0.296%

    No Known Activations