© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95454
    Prev
    Next
    INDEX
    Explanations

    references to societal and cultural perceptions of power dynamics and privilege

    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
    age
    -0.07
    v
    -0.06
    x
    -0.06
    l
    -0.06
    agens
    -0.06
    -0.06
    chter
    -0.06
    ify
    -0.06
     sl
    -0.06
    f
    -0.06
    POSITIVE LOGITS
    Insets
    0.08
    oÄŁ
    0.08
    ìľ¡
    0.07
    PerPixel
    0.07
    ãĥ¬ãĥĥãĥĪ
    0.07
    .fig
    0.07
    ÅĻez
    0.07
    .tp
    0.06
    idel
    0.06
    olet
    0.06
    Activations Density 0.280%

    No Known Activations