© 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. 77503
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate social dynamics or inequality

    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
    ामà¤Ĺ
    -0.07
    itoris
    -0.07
    alte
    -0.06
    hausen
    -0.06
    bé
    -0.06
    itori
    -0.06
     didFinish
    -0.06
    ouses
    -0.06
    loadModel
    -0.06
     Sexe
    -0.06
    POSITIVE LOGITS
     applicable
    0.08
    .apply
    0.07
     Apply
    0.07
    Apply
    0.07
     occurrences
    0.07
     apply
    0.07
     Occ
    0.07
     Applies
    0.07
    apply
    0.07
     пÑĢимен
    0.07
    Activations Density 0.044%

    No Known Activations