© 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. 38593
    Prev
    Next
    INDEX
    Explanations

    HTML script tags and related elements

    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
    ÑĢÑı
    -0.06
     Inf
    -0.06
     Bucc
    -0.06
    INF
    -0.06
     buc
    -0.06
     Fat
    -0.06
     Alexand
    -0.05
    tainment
    -0.05
     fat
    -0.05
    (ed
    -0.05
    POSITIVE LOGITS
    rement
    0.08
    Chan
    0.07
     Chan
    0.07
    rior
    0.07
    mdb
    0.07
    awl
    0.07
    rette
    0.07
    ·»
    0.06
    irty
    0.06
    .UseVisualStyleBackColor
    0.06
    Activations Density 0.008%

    No Known Activations