© 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. 62048
    Prev
    Next
    INDEX
    Explanations

    instances of failure or negligence

    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
    anko
    -0.08
    ìĭĿ
    -0.08
    olle
    -0.08
    ẻ
    -0.08
     Ziel
    -0.08
    amba
    -0.07
    .mixin
    -0.07
    nett
    -0.07
    ulle
    -0.07
    apl
    -0.07
    POSITIVE LOGITS
     to
    0.11
    614
    0.06
    insky
    0.06
    417
    0.06
     whole
    0.05
     shifting
    0.05
    plus
    0.05
     upper
    0.05
    216
    0.05
     con
    0.05
    Activations Density 0.006%

    No Known Activations