© 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. 73645
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and options

    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
    hape
    -0.06
    iant
    -0.06
    ile
    -0.06
    asco
    -0.06
    bilt
    -0.06
    til
    -0.06
    ivant
    -0.06
    itz
    -0.06
    swagen
    -0.06
    axon
    -0.06
    POSITIVE LOGITS
    licas
    0.07
    edik
    0.07
    lias
    0.07
    coes
    0.06
    celed
    0.06
    ega
    0.06
    ÑĢава
    0.06
    inalg
    0.06
    вен
    0.06
    ÅĻez
    0.06
    Activations Density 0.033%

    No Known Activations