© 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. 130538
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "At" followed by a non-zero numerical value

    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
    tas
    -0.08
    erland
    -0.07
    duct
    -0.07
    esc
    -0.06
     Miy
    -0.06
    verter
    -0.06
    verts
    -0.06
    haft
    -0.06
    imations
    -0.06
     favour
    -0.06
    POSITIVE LOGITS
    itler
    0.07
    gne
    0.07
    czas
    0.07
    ihan
    0.07
    702
    0.07
    aliz
    0.07
    APPER
    0.06
    agua
    0.06
    Argb
    0.06
    KF
    0.06
    Activations Density 0.030%

    No Known Activations