© 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 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. 17-LLAMASCOPE-RES-131K
    11. 84192
    Prev
    Next
    INDEX
    Explanations

    phrases indicating concerns about consultation and decision-making impact on businesses

    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
     _______,
    -0.09
    ̣
    -0.09
    (æ°´
    -0.08
    .SendMessage
    -0.08
    .timing
    -0.08
    .DropDown
    -0.08
    Äįel
    -0.08
    oppable
    -0.08
    ï¿¥
    -0.07
     alıp
    -0.07
    POSITIVE LOGITS
    .↵
    0.08
     its
    0.07
     â
    0.07
     —
    0.06
     .↵
    0.06
     –
    0.06
     others
    0.06
    ?↵
    0.06
    ".↵
    0.05
    abol
    0.05
    Activations Density 0.109%

    No Known Activations