© 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 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. 118807
    Prev
    Next
    INDEX
    Explanations

    information related to popular trends and people's actions

    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
    linger
    -0.07
     EDGE
    -0.07
    IRT
    -0.07
    ething
    -0.06
     Ridge
    -0.06
    inae
    -0.06
    auge
    -0.06
    ford
    -0.06
    ãĥĥãĤ«ãĥ¼
    -0.06
    zs
    -0.06
    POSITIVE LOGITS
    @nate
    0.08
    opy
    0.07
    ModelProperty
    0.07
    Ð®ÐĽ
    0.07
    pany
    0.07
    435
    0.07
    ÙĪتر
    0.06
    lear
    0.06
    ery
    0.06
     themselves
    0.06
    Activations Density 0.011%

    No Known Activations