© 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. 15-LLAMASCOPE-RES-131K
    11. 26961
    Prev
    Next
    INDEX
    Explanations

    terms related to social and economic class distinctions

    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
    lue
    -0.07
    geh
    -0.07
    pesan
    -0.07
    =post
    -0.07
    μοί
    -0.07
    اÙĦÙĬ
    -0.07
    anyak
    -0.07
    undry
    -0.07
    å«
    -0.07
    mpar
    -0.06
    POSITIVE LOGITS
    /uploads
    0.06
    ones
    0.06
    444
    0.06
     multer
    0.06
    anta
    0.06
    -ÑĤо
    0.06
    tract
    0.06
     nations
    0.06
    incess
    0.06
     prec
    0.05
    Activations Density 0.104%

    No Known Activations