© 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. 2750
    Prev
    Next
    INDEX
    Explanations

    references to measurements, components, and specifics related to technical or structured subjects, particularly in artistic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Common grammatical elements or connecting words in different languages, often appearing between content words to provide structure to the text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ournals
    -0.07
    éļ
    -0.06
    andon
    -0.06
     Jarvis
    -0.06
    EI
    -0.06
    ifton
    -0.06
    inance
    -0.06
    ASET
    -0.05
     markers
    -0.05
     hors
    -0.05
    POSITIVE LOGITS
    teri
    0.07
    IMIT
    0.07
     authDomain
    0.07
    vailability
    0.07
    cape
    0.07
     Dove
    0.07
    engin
    0.07
    .mas
    0.07
     apo
    0.07
    StackNavigator
    0.06
    Activations Density 0.240%

    No Known Activations