© 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. 106222
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Angela" or variations of it

    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
    'gc
    -0.08
    æľĭ
    -0.07
    .gameserver
    -0.07
     NotSupportedException
    -0.07
    heid
    -0.07
    itive
    -0.07
    kea
    -0.07
    haps
    -0.07
    ernen
    -0.07
    Ñī
    -0.07
    POSITIVE LOGITS
    els
    0.08
    ed
    0.07
    ri
    0.06
    ELS
    0.06
    liches
    0.06
    lo
    0.06
     Ang
    0.06
    U
    0.06
    èĶµ
    0.06
    uler
    0.06
    Activations Density 0.005%

    No Known Activations