© 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. 17-LLAMASCOPE-RES-131K
    11. 3995
    Prev
    Next
    INDEX
    Explanations

    programming-related functions and methods

    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
    bject
    -0.08
    (æ°´
    -0.07
    abbrev
    -0.07
    rypton
    -0.07
    ómo
    -0.07
    awns
    -0.07
    ermann
    -0.07
    venes
    -0.07
     orm
    -0.07
    POSITIVE LOGITS
    neh
    0.06
    at
    0.06
    hir
    0.06
    itm
    0.06
    OP
    0.05
    extra
    0.05
    ("(%
    0.05
     Williamson
    0.05
     Cres
    0.05
    اÙĬØ©
    0.05
    Activations Density 0.004%

    No Known Activations