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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17542
    Prev
    Next
    INDEX
    Explanations

    instances of control flow statements, particularly break and continue

    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
    fab
    -0.08
    disposing
    -0.07
    cre
    -0.07
    ire
    -0.07
    nap
    -0.06
    Ul
    -0.06
    éo
    -0.06
     fab
    -0.06
    ernet
    -0.06
    OA
    -0.06
    POSITIVE LOGITS
    KERNEL
    0.07
    icorn
    0.07
    åı·
    0.07
    usra
    0.06
     nor
    0.06
    orthand
    0.06
    919
    0.06
    vens
    0.06
    LLL
    0.06
    asso
    0.06
    Activations Density 0.004%

    No Known Activations