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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74699
    Prev
    Next
    INDEX
    Explanations

    attributes and properties within programming or code structures

    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
     dre
    -0.06
     (
    -0.06
    (
    -0.06
    omal
    -0.06
     Gaines
    -0.06
    hu
    -0.06
    ä¾
    -0.06
    erto
    -0.05
    qli
    -0.05
     corp
    -0.05
    POSITIVE LOGITS
     oppon
    0.08
    kowski
    0.07
    .scalablytyped
    0.07
    .UnitTesting
    0.07
    .usermodel
    0.07
    åįļçī©
    0.06
    ãĥĩãĤ£ãĥ¼ãĤ¹
    0.06
    енÑģ
    0.06
    ãĥ¼ãĥĨãĤ£
    0.06
    nett
    0.06
    Activations Density 0.005%

    No Known Activations