© 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. 57361
    Prev
    Next
    INDEX
    Explanations

    operations related to data storage and manipulation

    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
    olson
    -0.07
    yll
    -0.07
    354
    -0.06
     prior
    -0.06
     ÑĢаÑģ
    -0.06
     Josef
    -0.06
    ssf
    -0.05
     Robertson
    -0.05
    rollo
    -0.05
    vn
    -0.05
    POSITIVE LOGITS
    _into
    0.11
    Into
    0.10
    into
    0.10
     onto
    0.10
     vÃło
    0.09
     into
    0.09
    onto
    0.09
    zac
    0.08
    uib
    0.08
     Into
    0.08
    Activations Density 0.040%

    No Known Activations