© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88010
    Prev
    Next
    INDEX
    Explanations

    actions related to packing and preparation for travel or events

    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
     actionTypes
    -0.07
    ghi
    -0.07
    andel
    -0.07
    gaard
    -0.06
     pione
    -0.06
     optarg
    -0.06
    pect
    -0.06
    anou
    -0.06
    idon
    -0.06
    PECT
    -0.06
    POSITIVE LOGITS
    _fixture
    0.07
    .TableLayoutPanel
    0.06
    pst
    0.06
     Herz
    0.06
    ìķ½
    0.06
     Kre
    0.06
    Nonnull
    0.06
    ôn
    0.06
    )&&
    0.06
    Grab
    0.06
    Activations Density 0.032%

    No Known Activations