© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87357
    Prev
    Next
    INDEX
    Explanations

    components related to narrative structure and critical reviews

    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
     midd
    -0.06
    752
    -0.06
    055
    -0.06
    ffa
    -0.06
     temporarily
    -0.06
    rench
    -0.06
    δÏģα
    -0.06
    preh
    -0.06
     ابتد
    -0.06
    fork
    -0.06
    POSITIVE LOGITS
     final
    0.30
    final
    0.24
    -final
    0.23
     Final
    0.23
     finale
    0.23
     FINAL
    0.22
    æľĢåIJİ
    0.21
     cuá»iji
    0.21
    Final
    0.21
    _final
    0.20
    Activations Density 0.232%

    No Known Activations