© 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. 9-LLAMASCOPE-RES-131K
    11. 95756
    Prev
    Next
    INDEX
    Explanations

    components related to genetic techniques and information 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
    curring
    -0.06
    iosa
    -0.06
    ondheim
    -0.06
    egin
    -0.06
    rega
    -0.06
     tinh
    -0.06
     ragaz
    -0.06
    cha
    -0.06
    uet
    -0.06
    amodel
    -0.06
    POSITIVE LOGITS
    htar
    0.07
    زد
    0.07
    OutOfRange
    0.06
    ÙĴÙħ
    0.06
     Conv
    0.06
     so
    0.06
    .blank
    0.06
     mül
    0.06
    ToSend
    0.06
    iglia
    0.06
    Activations Density 0.117%

    No Known Activations