© 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. 73362
    Prev
    Next
    INDEX
    Explanations

    requests related to completing or filling out forms

    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
    out
    -0.07
    -0.06
    :
    -0.06
     scouting
    -0.06
     themselves
    -0.06
    osto
    -0.06
    andy
    -0.06
    outers
    -0.05
     settles
    -0.05
     gre
    -0.05
    POSITIVE LOGITS
     below
    0.10
     ниже
    0.08
    conds
    0.08
     BELOW
    0.08
    ãĥ¼ãĥł
    0.08
    iglia
    0.08
     vá»ijn
    0.08
     eksik
    0.07
     fields
    0.07
     Below
    0.07
    Activations Density 0.004%

    No Known Activations