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

    Neuronpedia

    Jacobian LensNEW
    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. 128905
    Prev
    Next
    INDEX
    Explanations

    incidents involving crime or law enforcement

    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
    agy
    -0.07
     extras
    -0.06
     prolific
    -0.06
     retreat
    -0.06
    pine
    -0.06
    ragon
    -0.06
     diffs
    -0.06
    falls
    -0.05
     asteroid
    -0.05
    éĽ²
    -0.05
    POSITIVE LOGITS
     barg
    0.08
     pier
    0.08
     Pier
    0.08
    icon
    0.07
    abbo
    0.07
    å±
    0.07
     quay
    0.07
    shm
    0.07
    istra
    0.07
     terminals
    0.07
    Activations Density 0.068%

    No Known Activations