© 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. 118726
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causal relationships and conditional 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
    cola
    -0.07
     lecken
    -0.07
    meyi
    -0.07
    ÑĸйÑģ
    -0.07
     {{{
    -0.07
     ì§Ī
    -0.07
    postalcode
    -0.06
    ocracy
    -0.06
    ptal
    -0.06
    uby
    -0.06
    POSITIVE LOGITS
     many
    0.09
    many
    0.07
    Looper
    0.07
     often
    0.07
    Many
    0.07
     some
    0.07
    airy
    0.06
    igue
    0.06
    gone
    0.06
    some
    0.06
    Activations Density 0.157%

    No Known Activations