© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 104041
    Prev
    Next
    INDEX
    Explanations

    occurrences of time-related phrases or markers

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    )NULL
    -0.06
    ColumnsMode
    -0.06
    HT
    -0.06
    jte
    -0.05
    jam
    -0.05
     qualitative
    -0.05
    uki
    -0.05
    ght
    -0.05
    'gc
    -0.05
    odore
    -0.05
    POSITIVE LOGITS
    amet
    0.08
     ún
    0.08
    hazi
    0.07
    anela
    0.07
    ynamics
    0.07
    mdir
    0.07
    ìĬ¤íĨł
    0.07
    à¥Ģल
    0.07
    inesis
    0.06
    _https
    0.06
    Activations Density 0.001%

    No Known Activations