© 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. 59017
    Prev
    Next
    INDEX
    Explanations

    references to regulatory bodies and guidelines related to nuclear waste management

    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
    ib
    -0.08
    of
    -0.07
     preliminary
    -0.07
    elen
    -0.07
    gren
    -0.07
    erson
    -0.07
    ene
    -0.07
    c
    -0.07
    em
    -0.07
    ire
    -0.07
    POSITIVE LOGITS
    iginal
    0.11
    hea
    0.10
    erer
    0.10
    uncated
    0.09
    hythm
    0.09
    zÄħd
    0.09
    .scalablytyped
    0.08
    efined
    0.08
    senal
    0.08
    ourke
    0.08
    Activations Density 0.070%

    No Known Activations