© 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 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. 17-LLAMASCOPE-RES-131K
    11. 88760
    Prev
    Next
    INDEX
    Explanations

    instances of multiplication or pointer dereferencing 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
    umpt
    -0.08
    Caption
    -0.06
    itus
    -0.06
    Ãłn
    -0.06
    lland
    -0.06
    oland
    -0.06
    iken
    -0.06
    ÑģÑı
    -0.06
    .uk
    -0.06
    otto
    -0.06
    POSITIVE LOGITS
    elay
    0.07
    602
    0.06
    ©
    0.06
     Award
    0.06
    241
    0.06
    FORCE
    0.06
    fluid
    0.06
    245
    0.06
     slova
    0.06
     Forces
    0.06
    Activations Density 0.002%

    No Known Activations