© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60251
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory or legislative contexts

    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
    ey
    -0.14
    erson
    -0.11
    ek
    -0.10
    ee
    -0.10
    eer
    -0.10
    ego
    -0.10
    y
    -0.10
    es
    -0.10
    ei
    -0.09
    ef
    -0.09
    POSITIVE LOGITS
    iginal
    0.13
    hythm
    0.11
    outines
    0.09
    hyth
    0.09
    leans
    0.08
    IENTATION
    0.08
    aleigh
    0.08
    er
    0.08
    izont
    0.08
    chestra
    0.08
    Activations Density 0.091%

    No Known Activations