© 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. 61185
    Prev
    Next
    INDEX
    Explanations

    discussions of personal experiences with societal challenges and discrimination

    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
    pun
    -0.07
     pun
    -0.07
    fak
    -0.07
    -UA
    -0.07
    scoped
    -0.06
    (IL
    -0.06
    Ngh
    -0.06
     Families
    -0.06
    <TEntity
    -0.06
     faults
    -0.06
    POSITIVE LOGITS
     experiences
    0.08
     discrimination
    0.08
     encounters
    0.07
     racial
    0.07
     harassment
    0.07
     experience
    0.07
     encounter
    0.07
     rac
    0.07
     racism
    0.06
     experienced
    0.06
    Activations Density 0.047%

    No Known Activations