© 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. 15-LLAMASCOPE-RES-131K
    11. 90609
    Prev
    Next
    INDEX
    Explanations

    topics related to abortion and the characteristics of a fetus

    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
    ingers
    -0.07
    aines
    -0.07
     Chronic
    -0.06
     chrono
    -0.06
    rone
    -0.06
    nÃŃky
    -0.06
    ologia
    -0.06
     ziy
    -0.06
     INCIDENT
    -0.06
    remen
    -0.06
    POSITIVE LOGITS
     gest
    0.07
     Human
    0.07
     motion
    0.07
    Human
    0.07
    Uniform
    0.07
    gest
    0.07
     human
    0.07
     stages
    0.06
     cellular
    0.06
     staging
    0.06
    Activations Density 0.004%

    No Known Activations