© 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. 9-LLAMASCOPE-RES-131K
    11. 96884
    Prev
    Next
    INDEX
    Explanations

    transactional and historical details in a narrative

    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
    anchor
    -0.07
    008
    -0.06
    Äĩi
    -0.06
    esta
    -0.06
    aniu
    -0.06
     IDR
    -0.06
    ephir
    -0.06
    |RF
    -0.06
    amarin
    -0.06
    056
    -0.06
    POSITIVE LOGITS
    inning
    0.07
    'gc
    0.07
    aset
    0.07
    æĮģãģ¡
    0.07
    rolley
    0.07
    ureau
    0.06
    ÑĥÑĢн
    0.06
    eway
    0.06
    UTTON
    0.06
    acha
    0.06
    Activations Density 0.007%

    No Known Activations