© 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. 108064
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or associations, particularly involving the word "with."

    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
    .asc
    -0.07
    adem
    -0.06
    .metamodel
    -0.06
    laws
    -0.06
    zu
    -0.06
    /from
    -0.06
    xmm
    -0.06
    .av
    -0.06
    .inline
    -0.06
    ÏĥÏĦά
    -0.06
    POSITIVE LOGITS
     regard
    0.09
     regards
    0.08
     respect
    0.07
    ument
    0.06
    /fw
    0.06
    ugh
    0.06
    associated
    0.06
    -in
    0.06
     associated
    0.06
     emphasis
    0.06
    Activations Density 0.051%

    No Known Activations