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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1560
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, particularly those associated with memory management in Objective-C

    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
    ingo
    -0.08
    icari
    -0.07
    kili
    -0.07
    inton
    -0.07
    olo
    -0.07
    ysa
    -0.07
    noinspection
    -0.07
    ikipedia
    -0.07
    ighton
    -0.06
    vala
    -0.06
    POSITIVE LOGITS
    ity
    0.06
    ëł¹
    0.06
    oenix
    0.06
    ivil
    0.06
     habit
    0.06
    .gdx
    0.06
     Shannon
    0.05
     Kurt
    0.05
     Mits
    0.05
    /Internal
    0.05
    Activations Density 0.001%

    No Known Activations