© 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 EvalsExportsinterp-engineNEWAPI 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. 88795
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly those with unique or notable names

    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
    ma
    -0.13
    men
    -0.11
    mi
    -0.11
    ness
    -0.11
    pa
    -0.11
    me
    -0.11
    mas
    -0.11
    li
    -0.10
    pu
    -0.10
    mat
    -0.10
    POSITIVE LOGITS
    yar
    0.11
    yaw
    0.10
    ê¹
    0.10
    SSION
    0.09
    yat
    0.09
    embros
    0.09
    ya
    0.09
    yah
    0.08
    ÅĽmy
    0.08
    Leaks
    0.08
    Activations Density 0.308%

    No Known Activations