© 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. 30287
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal actions and legal cases

    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
    adece
    -0.08
    ennis
    -0.07
    Łèĥ½
    -0.07
    ight
    -0.07
    ADR
    -0.07
    loquent
    -0.07
    rim
    -0.07
     دستÛĮ
    -0.07
     Murder
    -0.07
     QUERY
    -0.06
    POSITIVE LOGITS
     case
    0.07
     evidence
    0.06
     according
    0.06
    ụ
    0.06
     false
    0.06
    sville
    0.06
     investigation
    0.06
     greed
    0.06
     mod
    0.06
    invest
    0.06
    Activations Density 0.025%

    No Known Activations