© 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. 61290
    Prev
    Next
    INDEX
    Explanations

    references to crime and legal actions

    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
     milan
    -0.07
     detention
    -0.07
    duk
    -0.07
    street
    -0.07
    γι
    -0.07
    jist
    -0.07
     беÑģ
    -0.07
     detain
    -0.06
    ÑĨвеÑĤ
    -0.06
    abaj
    -0.06
    POSITIVE LOGITS
     motive
    0.08
    ints
    0.07
    oves
    0.06
    owi
    0.06
     motives
    0.06
    oved
    0.06
    abilia
    0.06
    olution
    0.06
    owie
    0.06
    моÑĤ
    0.06
    Activations Density 0.039%

    No Known Activations