© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18512
    Prev
    Next
    INDEX
    Explanations

    the word "construed" and its variations, indicating a focus on interpretation or understanding of legal or formal language

    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
    strar
    -0.07
    e
    -0.06
    iard
    -0.06
    y
    -0.06
    arden
    -0.06
    ode
    -0.06
    t
    -0.06
    ing
    -0.06
    o
    -0.06
    acÃŃ
    -0.06
    POSITIVE LOGITS
    amics
    0.08
    loyment
    0.08
    ushima
    0.07
    ancies
    0.07
    ERA
    0.07
    appable
    0.07
    ãģĺ
    0.07
    ÙĦاÙĦ
    0.07
    бав
    0.07
    $MESS
    0.07
    Activations Density 0.002%

    No Known Activations