© 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 EvalsExportsinterp-engineNEWAPI 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. 31326
    Prev
    Next
    INDEX
    Explanations

    references to crime and government response to it

    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
     POLITICO
    -0.08
    estone
    -0.07
    uess
    -0.07
    @testable
    -0.06
     unut
    -0.06
    enger
    -0.06
    ength
    -0.06
    GMT
    -0.06
    VML
    -0.06
    leyen
    -0.06
    POSITIVE LOGITS
    аÑĤом
    0.06
     Works
    0.06
     value
    0.06
    ovit
    0.06
    value
    0.06
    705
    0.06
    hai
    0.05
    amac
    0.05
    criptions
    0.05
    ortal
    0.05
    Activations Density 0.016%

    No Known Activations