© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97298
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names

    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
    igner
    -0.07
    ÑĢоÑĪ
    -0.07
    лоÑĤ
    -0.07
     èª
    -0.06
    ein
    -0.06
    ÑĢаж
    -0.06
    cala
    -0.06
    ey
    -0.06
    icast
    -0.06
    akan
    -0.06
    POSITIVE LOGITS
    cano
    0.07
     Yaz
    0.07
    udad
    0.07
    caf
    0.06
    affe
    0.06
    orc
    0.06
    369
    0.06
    hcp
    0.06
    azel
    0.06
    ysics
    0.06
    Activations Density 0.001%

    No Known Activations