© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4398
    Prev
    Next
    INDEX
    Explanations

    numerical values or references that likely relate to statistical data or identifiers

    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
     verg
    -0.06
    aso
    -0.06
     Minerals
    -0.06
    ayah
    -0.06
    .vo
    -0.06
    asio
    -0.06
    wine
    -0.06
    .Sdk
    -0.06
    edenÃŃ
    -0.06
     خاÙĨ
    -0.06
    POSITIVE LOGITS
    htdocs
    0.08
    errar
    0.06
    CHIP
    0.06
     tent
    0.06
    quia
    0.06
    éru
    0.06
    radu
    0.06
    RACT
    0.06
    elop
    0.06
    òi
    0.06
    Activations Density 0.044%

    No Known Activations