Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11488
    Prev
    Next
    INDEX
    Explanations

    references to chronology or time-related themes

    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
    ÏĪη
    -0.07
    ollar
    -0.07
    tuk
    -0.07
    t
    -0.07
    ehen
    -0.07
    ouden
    -0.07
    ainen
    -0.07
    ermo
    -0.06
    uil
    -0.06
    enses
    -0.06
    POSITIVE LOGITS
    icles
    0.16
    icle
    0.16
    ological
    0.12
    ICLE
    0.12
    ICLES
    0.11
    ometer
    0.11
    ograph
    0.11
    ology
    0.10
    ographs
    0.10
    iques
    0.10
    Activations Density 0.004%

    No Known Activations