© 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. 17-LLAMASCOPE-RES-131K
    11. 94276
    Prev
    Next
    INDEX
    Explanations

    references to menstrual health and related experiences

    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
    asd
    -0.07
    loit
    -0.06
    -flat
    -0.06
    inge
    -0.06
    idar
    -0.06
    iny
    -0.06
    ",__
    -0.06
    oins
    -0.06
     DESCRIPTION
    -0.06
    inyin
    -0.06
    POSITIVE LOGITS
     pledge
    0.08
     pledged
    0.07
    action
    0.07
    ?url
    0.07
     pledges
    0.07
     commitments
    0.07
    azon
    0.07
    .UR
    0.06
    pled
    0.06
     pled
    0.06
    Activations Density 0.009%

    No Known Activations