© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119113
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to the struggles and experiences of women, particularly in historical contexts

    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
    porte
    -0.08
    823
    -0.07
    enson
    -0.06
    ILD
    -0.06
    oud
    -0.06
    achel
    -0.06
    ceans
    -0.06
    .gs
    -0.06
    Subscriber
    -0.06
    Ð¡Ð¡Ðł
    -0.06
    POSITIVE LOGITS
     Sanat
    0.07
     kum
    0.07
    oh
    0.07
     Cem
    0.07
    mem
    0.07
    adic
    0.06
    arness
    0.06
    vant
    0.06
    sgi
    0.06
    umbnail
    0.06
    Activations Density 0.002%

    No Known Activations