© 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. 73851
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically periods, indicating the end of sentences

    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
    iglia
    -0.07
    mada
    -0.07
    fid
    -0.07
    ogui
    -0.07
    loth
    -0.07
    γη
    -0.07
    ãĥ¼ãĥĬ
    -0.06
     заг
    -0.06
    ứ
    -0.06
    OVE
    -0.06
    POSITIVE LOGITS
    ocrat
    0.07
     mur
    0.06
    ur
    0.06
     Ald
    0.06
     style
    0.06
     ald
    0.06
    Source
    0.06
    und
    0.06
    594
    0.06
    ci
    0.05
    Activations Density 0.000%

    No Known Activations