© 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. 70165
    Prev
    Next
    INDEX
    Explanations

    phrases indicating skepticism or qualification in statements

    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
    herits
    -0.07
    deposit
    -0.07
     Hindered
    -0.07
    batim
    -0.07
     Hlav
    -0.07
    EdgeInsets
    -0.07
    -ÑĤаки
    -0.07
    assis
    -0.06
    ÙĪÙĤع
    -0.06
    Deposit
    -0.06
    POSITIVE LOGITS
     say
    0.08
     necessarily
    0.07
    udd
    0.07
    say
    0.07
     saying
    0.07
    oggler
    0.06
    xious
    0.06
    說
    0.06
     says
    0.06
    RAINT
    0.06
    Activations Density 0.002%

    No Known Activations