© 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. 94067
    Prev
    Next
    INDEX
    Explanations

    curly braces, indicating the start of code blocks or structures

    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
    esz
    -0.07
    ji
    -0.06
     Gabri
    -0.06
    loor
    -0.06
     Tight
    -0.06
    ãĤº
    -0.06
    ahi
    -0.06
     Zi
    -0.06
    esti
    -0.05
     åIJ
    -0.05
    POSITIVE LOGITS
    ncpy
    0.07
    urope
    0.07
    irut
    0.06
     class
    0.06
    ullan
    0.06
     reserve
    0.06
    vation
    0.06
     respawn
    0.06
    brtc
    0.06
    ë¥ĺ
    0.06
    Activations Density 0.001%

    No Known Activations