© 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. 15-LLAMASCOPE-RES-131K
    6. 62188
    Prev
    Next
    INDEX
    Explanations

    references to historical or significant events and concepts related to societal issues

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

    Words representing significant temporal events, seasons, weather conditions, or procedural moments that serve as contextual anchors in 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
    ERP
    -0.07
    antz
    -0.07
     stamps
    -0.07
    isches
    -0.07
    avan
    -0.06
    avou
    -0.06
    iones
    -0.06
    gra
    -0.06
     Foo
    -0.06
     Consulting
    -0.06
    POSITIVE LOGITS
    žil
    0.07
    stdin
    0.07
    uš
    0.07
    ousse
    0.07
    æĺİ
    0.07
     $("#"
    0.06
    enk
    0.06
    INVAL
    0.06
    988
    0.06
    æľŁéĹ´
    0.06
    Activations Density 0.041%

    No Known Activations