Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43533
    Prev
    Next
    INDEX
    Explanations

    phrases related to police interactions and accountability

    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
    aille
    -0.07
    Severity
    -0.07
     ìĨ
    -0.06
     bÃło
    -0.06
    spm
    -0.06
    spy
    -0.06
    ptom
    -0.06
     mktime
    -0.06
    .borrow
    -0.06
    رÛĮÙħ
    -0.06
    POSITIVE LOGITS
     comply
    0.12
     complied
    0.12
     compliance
    0.11
     complying
    0.11
     surrender
    0.10
     compliant
    0.10
     Compliance
    0.10
     handc
    0.10
     cooperate
    0.10
     cooper
    0.10
    Activations Density 0.021%

    No Known Activations