© 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. 116703
    Prev
    Next
    INDEX
    Explanations

    elements related to form creation and data submission

    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
    ote
    -0.06
    etch
    -0.06
     McCorm
    -0.06
    oj
    -0.05
    ugar
    -0.05
     nhất
    -0.05
     feed
    -0.05
    added
    -0.05
    ary
    -0.05
    916
    -0.05
    POSITIVE LOGITS
    AFX
    0.08
    chas
    0.08
    \grid
    0.07
    оÑī
    0.07
     иÑģÑĤ
    0.07
    vek
    0.07
    itsu
    0.07
    instanc
    0.07
    chia
    0.07
    atk
    0.07
    Activations Density 0.018%

    No Known Activations