© 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. 82607
    Prev
    Next
    INDEX
    Explanations

    dates and years mentioned in the text

    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
    orde
    -0.07
    tuk
    -0.07
    erner
    -0.06
    ntax
    -0.06
    /proto
    -0.06
    OVE
    -0.06
    SED
    -0.06
    ëĶĶìĺ¤
    -0.06
    emer
    -0.06
    ierz
    -0.06
    POSITIVE LOGITS
    ç»ĵ
    0.08
     ê²°íĺ¼
    0.07
     Marriage
    0.07
    主義
    0.06
    addin
    0.06
     actresses
    0.06
     marriage
    0.06
    à¤Ĺल
    0.06
     mariage
    0.06
     coppia
    0.06
    Activations Density 0.004%

    No Known Activations