© 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 EvalsExportsAPI 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. 106165
    Prev
    Next
    INDEX
    Explanations

    attributes related to alignment and positioning in code or markup

    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
    ente
    -0.07
    aar
    -0.07
    -Sah
    -0.07
    .opensource
    -0.07
    indsight
    -0.07
    _MAXIMUM
    -0.07
    tement
    -0.07
    ISCO
    -0.07
    'gc
    -0.06
    orst
    -0.06
    POSITIVE LOGITS
    ColumnInfo
    0.06
    -cent
    0.06
    Checkpoint
    0.06
    Ùģات
    0.06
     inline
    0.05
    ?key
    0.05
     Gib
    0.05
    ondon
    0.05
    undefined
    0.05
    s
    0.05
    Activations Density 0.001%

    No Known Activations