© 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. 118808
    Prev
    Next
    INDEX
    Explanations

    instances of posting or announcements

    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
    855
    -0.06
    antz
    -0.06
    elder
    -0.06
    pl
    -0.06
    flip
    -0.06
    azzi
    -0.06
    anzi
    -0.06
    wei
    -0.06
    .www
    -0.06
    utes
    -0.06
    POSITIVE LOGITS
    oton
    0.07
    eck
    0.06
    ymm
    0.06
    eper
    0.06
    illac
    0.06
    tober
    0.06
    oder
    0.06
    inding
    0.06
    midd
    0.06
    ÐĽÐIJ
    0.06
    Activations Density 0.000%

    No Known Activations