© 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. 15370
    Prev
    Next
    INDEX
    Explanations

    logical operators and conditional expressions in code

    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
    ajar
    -0.08
    ajes
    -0.07
    cente
    -0.07
    enate
    -0.07
    enaries
    -0.07
    èĪ¬
    -0.07
    à¸Ĺร
    -0.07
    __$
    -0.07
    conference
    -0.07
    inee
    -0.07
    POSITIVE LOGITS
    acular
    0.07
     elevated
    0.06
    oreach
    0.06
     die
    0.06
     su
    0.06
    "\↵
    0.06
    uin
    0.05
    çĤ¸
    0.05
    IENTATION
    0.05
    اذ
    0.05
    Activations Density 0.001%

    No Known Activations