© 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. 9-LLAMASCOPE-RES-131K
    11. 97412
    Prev
    Next
    INDEX
    Explanations

    references to police activity and investigations

    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
    GGLE
    -0.07
    asons
    -0.06
    354
    -0.06
     insp
    -0.06
    agg
    -0.06
     (
    -0.06
    ilee
    -0.06
    åģ
    -0.06
    adi
    -0.05
     aud
    -0.05
    POSITIVE LOGITS
    Intialized
    0.07
     zoek
    0.07
    OffsetTable
    0.07
    .Unity
    0.07
    kdir
    0.07
    jis
    0.07
    ucu
    0.07
     (*((
    0.06
    @Spring
    0.06
     ActiveForm
    0.06
    Activations Density 0.022%

    No Known Activations