© 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. 69510
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "at" and related phrases indicating location or presence

    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
     rám
    -0.08
    à¤Ĥà¤ľ
    -0.07
    /tutorial
    -0.07
    ÙĦع
    -0.07
    raq
    -0.06
    agh
    -0.06
    ále
    -0.06
    LOB
    -0.06
    sher
    -0.06
    dn
    -0.06
    POSITIVE LOGITS
    ibo
    0.07
    eless
    0.06
    trap
    0.06
    eydi
    0.06
    ovation
    0.06
    ãĥĬãĥ¼
    0.06
     Stamp
    0.06
    bye
    0.06
     Tracks
    0.06
     Shooter
    0.06
    Activations Density 0.020%

    No Known Activations