Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29467
    Prev
    Next
    INDEX
    Explanations

    terms related to social and economic structures or inequalities

    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
    annis
    -0.08
    krom
    -0.08
     Ear
    -0.08
    ustum
    -0.07
    woods
    -0.07
    uchs
    -0.07
    aille
    -0.07
    عر
    -0.07
    uela
    -0.07
    Ñģим
    -0.07
    POSITIVE LOGITS
     who
    0.08
     whom
    0.08
     intact
    0.08
     whose
    0.07
    787
    0.07
    who
    0.06
    icia
    0.06
    whose
    0.06
     backing
    0.06
    otine
    0.05
    Activations Density 0.044%

    No Known Activations