© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74549
    Prev
    Next
    INDEX
    Explanations

    references to female subjects or characters

    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
    ilos
    -0.07
    180
    -0.06
    184
    -0.06
    202
    -0.06
    нÑĸÑĪ
    -0.06
    меÑĩ
    -0.06
    DN
    -0.06
    @nate
    -0.06
     helicopt
    -0.06
    arta
    -0.06
    POSITIVE LOGITS
    ureau
    0.07
    cope
    0.07
    ãĥ¼ãĤ¯
    0.07
    rique
    0.07
     NSK
    0.07
    ÑĢап
    0.06
    å·
    0.06
    ostel
    0.06
     hik
    0.06
    oola
    0.06
    Activations Density 0.000%

    No Known Activations