© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82266
    Prev
    Next
    INDEX
    Explanations

    numerical ratings or scores

    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
    759
    -0.06
    .heroku
    -0.06
    aliz
    -0.06
    Ñĥли
    -0.06
     bat
    -0.06
    uta
    -0.06
    Ymd
    -0.06
    ptic
    -0.06
    lication
    -0.06
    ủ
    -0.06
    POSITIVE LOGITS
     rated
    0.07
    amax
    0.07
    etections
    0.06
     Anonymous
    0.06
    åīĽ
    0.06
    umer
    0.06
     Crescent
    0.06
    QtCore
    0.06
     providedIn
    0.06
    uv
    0.06
    Activations Density 0.000%

    No Known Activations