© 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. 120371
    Prev
    Next
    INDEX
    Explanations

    the presence of release dates or announcements for music albums or events

    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
    éĥ¡
    -0.06
    boro
    -0.06
     worst
    -0.06
    antal
    -0.06
     Worst
    -0.06
    344
    -0.06
    orough
    -0.06
    incinn
    -0.06
    otten
    -0.06
    ÙĪبة
    -0.06
    POSITIVE LOGITS
    Streamer
    0.07
     VERIFY
    0.07
    imit
    0.07
    antaged
    0.07
    .fastjson
    0.07
    ικο
    0.06
    ordin
    0.06
    VERIFY
    0.06
    pond
    0.06
    CJK
    0.06
    Activations Density 0.001%

    No Known Activations