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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44013
    Prev
    Next
    INDEX
    Explanations

    coded language related to political or social categorization

    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
    i
    -0.17
    iš
    -0.09
    iou
    -0.09
    iag
    -0.09
    oze
    -0.08
    aft
    -0.08
    e
    -0.08
    o
    -0.08
    horse
    -0.08
    s
    -0.08
    POSITIVE LOGITS
    chi
    0.10
    ulent
    0.10
    uc
    0.09
    chin
    0.09
    cher
    0.09
    cee
    0.09
    ucus
    0.09
    ifer
    0.09
    chio
    0.09
    ucu
    0.09
    Activations Density 0.007%

    No Known Activations