© 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. 9-LLAMASCOPE-RES-131K
    11. 99079
    Prev
    Next
    INDEX
    Explanations

    phrases related to access restrictions and permissions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    lak
    -0.06
    inka
    -0.06
    Clickable
    -0.05
    ~/
    -0.05
     spiel
    -0.05
     prescriptions
    -0.05
    lei
    -0.05
    blog
    -0.05
    akes
    -0.05
     Geneva
    -0.05
    POSITIVE LOGITS
    RuleContext
    0.09
    adro
    0.08
    Ñīин
    0.08
    peria
    0.08
    éric
    0.08
    ãĥ³ãĤ¹
    0.08
     ziy
    0.07
    .Uint
    0.07
    ADX
    0.07
    ohl
    0.07
    Activations Density 0.000%

    No Known Activations