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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57037
    Prev
    Next
    INDEX
    Explanations

    references to policing and community safety initiatives

    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
    chw
    -0.08
     prosecuted
    -0.07
     prosecuting
    -0.07
    adin
    -0.07
    .Navigator
    -0.07
    eny
    -0.07
    resco
    -0.07
    ãĤ¶
    -0.07
    iste
    -0.07
     prosecute
    -0.07
    POSITIVE LOGITS
     police
    0.15
     crime
    0.14
     Police
    0.13
     law
    0.13
     Crime
    0.12
    Police
    0.11
    crime
    0.11
    Crime
    0.10
     security
    0.10
     Law
    0.09
    Activations Density 0.215%

    No Known Activations