© 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 EvalsExportsinterp-engineNEWAPI 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. 70128
    Prev
    Next
    INDEX
    Explanations

    names and references to individuals, particularly artists and historical figures

    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
    eph
    -0.08
    antha
    -0.08
    thur
    -0.07
    ska
    -0.07
    ef
    -0.06
    Ðİ
    -0.06
    bourg
    -0.06
    sip
    -0.06
    fty
    -0.06
    loth
    -0.06
    POSITIVE LOGITS
    веÑĤ
    0.07
    nung
    0.07
    gran
    0.07
    t
    0.06
    ervo
    0.06
    ÑİÑĢ
    0.06
    unce
    0.06
    antly
    0.06
    ADOS
    0.06
    ahl
    0.06
    Activations Density 0.012%

    No Known Activations