© 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. 17-LLAMASCOPE-RES-131K
    11. 130294
    Prev
    Next
    INDEX
    Explanations

    questions starting with "do" that invite inquiry or reflection

    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
    illis
    -0.08
    omik
    -0.07
    ils
    -0.07
    iek
    -0.07
    nat
    -0.07
    ]={↵
    -0.06
    apan
    -0.06
    htag
    -0.06
    etine
    -0.06
    LY
    -0.06
    POSITIVE LOGITS
    acas
    0.07
     bother
    0.07
     we
    0.06
    CAPE
    0.06
     flips
    0.06
    uers
    0.06
    akov
    0.06
    åľŃ
    0.06
    acom
    0.06
     why
    0.06
    Activations Density 0.003%

    No Known Activations