© 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. 128845
    Prev
    Next
    INDEX
    Explanations

    discussions about gender and representation in the arts

    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
    ron
    -0.08
    sky
    -0.07
    lius
    -0.07
    OTOR
    -0.06
    omor
    -0.06
    erin
    -0.06
    (ConfigurationManager
    -0.06
    él
    -0.06
    ÙİÙĤ
    -0.06
    TEX
    -0.06
    POSITIVE LOGITS
     unlike
    0.12
     unless
    0.08
    ibri
    0.07
     like
    0.07
     Unlike
    0.07
    åıĬåħ¶
    0.07
    ikat
    0.07
    eca
    0.07
    Unlike
    0.07
    δοÏĤ
    0.07
    Activations Density 0.037%

    No Known Activations