© 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. 22-LLAMASCOPE-RES-131K
    11. 3688
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks, particularly periods, within the text

    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
    a
    -0.08
    [
    -0.08
    y
    -0.07
    i
    -0.07
    l
    -0.07
    *
    -0.07
    en
    -0.07
    d
    -0.07
    es
    -0.07
    m
    -0.06
    POSITIVE LOGITS
    00
    0.09
    StackNavigator
    0.07
    SearchTree
    0.07
    Aceptar
    0.07
    .scalablytyped
    0.07
    ubyte
    0.07
    ụn
    0.07
    readcr
    0.07
    rious
    0.07
    TestFixture
    0.07
    Activations Density 0.092%

    No Known Activations