© 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. 72861
    Prev
    Next
    INDEX
    Explanations

    references to leather and related materials

    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
    884
    -0.07
    kie
    -0.07
    jid
    -0.07
    tur
    -0.07
    té
    -0.07
    naments
    -0.07
    yang
    -0.06
    ratings
    -0.06
    nga
    -0.06
    eko
    -0.06
    POSITIVE LOGITS
    ized
    0.10
    iminal
    0.08
    625
    0.08
    idge
    0.08
    like
    0.08
    licken
    0.08
    oid
    0.07
    itis
    0.07
    ised
    0.07
    iful
    0.07
    Activations Density 0.003%

    No Known Activations