© 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. 130483
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "unexpected" and its variations

    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
    atura
    -0.07
    aturas
    -0.07
    atus
    -0.07
    udev
    -0.07
    pack
    -0.07
    amba
    -0.06
    /Graphics
    -0.06
    qw
    -0.06
    isset
    -0.06
    eria
    -0.06
    POSITIVE LOGITS
    ably
    0.10
    ingly
    0.10
    ness
    0.10
    ively
    0.10
    ly
    0.09
    /un
    0.08
    aneously
    0.08
    ance
    0.07
    ments
    0.07
    ely
    0.07
    Activations Density 0.006%

    No Known Activations