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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 60917
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and entities

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

    Text fragments containing language-specific characters and word portions from Romance and Slavic languages, often related to geographical, historical, technical, or administrative terminology.

    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
    лиÑĤ
    -0.06
    ourn
    -0.06
    à¸Ĺย
    -0.06
    esthes
    -0.06
    ̧
    -0.06
    ,cp
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    лÑĥб
    -0.06
     mc
    -0.05
    utenberg
    -0.05
    POSITIVE LOGITS
    itsu
    0.08
    utilus
    0.07
    964
    0.07
    WER
    0.07
     Moines
    0.07
    OLON
    0.06
    aub
    0.06
    usercontent
    0.06
    ahren
    0.06
    inan
    0.06
    Activations Density 0.161%

    No Known Activations