© 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. 55999
    Prev
    Next
    INDEX
    Explanations

    phrases that express expectations or surprises related to outcomes

    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
    ħĮ
    -0.07
    dio
    -0.07
    ipse
    -0.07
    ableViewController
    -0.06
    IPS
    -0.06
    ESCO
    -0.06
    cef
    -0.06
     mev
    -0.06
    inois
    -0.06
    Ñĥков
    -0.06
    POSITIVE LOGITS
     surprising
    0.18
     surprises
    0.17
     surprisingly
    0.16
     surprise
    0.16
     surpr
    0.14
     surprised
    0.14
     Surprise
    0.14
     pÅĻekvap
    0.13
     unexpected
    0.12
    unexpected
    0.11
    Activations Density 0.034%

    No Known Activations