© 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. 82715
    Prev
    Next
    INDEX
    Explanations

    statements about identity and belonging, particularly related to marginalized groups

    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
    colo
    -0.08
    anter
    -0.06
    inton
    -0.06
    itti
    -0.06
     teklif
    -0.06
    неÑĤ
    -0.06
     Glas
    -0.06
    çģ
    -0.06
    .writ
    -0.06
    avana
    -0.06
    POSITIVE LOGITS
     instanceof
    0.08
     isa
    0.07
    ±
    0.06
    _IS
    0.06
    種
    0.06
     himself
    0.06
    å±ŀäºİ
    0.06
    Į
    0.06
     classified
    0.06
    anga
    0.06
    Activations Density 0.067%

    No Known Activations