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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5752
    Prev
    Next
    INDEX
    Explanations

    language related to cooperation with authorities

    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
    ãģ¡ãģ¯
    -0.08
    .AddListener
    -0.07
    اذ
    -0.07
    iliki
    -0.07
    .Suppress
    -0.07
    kaar
    -0.07
    enal
    -0.07
    'field
    -0.07
    ýt
    -0.07
    itzer
    -0.07
    POSITIVE LOGITS
     Cooper
    0.11
     cooperate
    0.10
     cooperation
    0.10
     Cooperation
    0.10
     cooper
    0.09
     cooperating
    0.09
     fully
    0.08
     cooperative
    0.08
     during
    0.07
    elli
    0.07
    Activations Density 0.004%

    No Known Activations