© 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. 88741
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax and structure, particularly related to string manipulation and command processing

    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
    eya
    -0.08
    .appspot
    -0.08
    aption
    -0.08
    itta
    -0.07
    igner
    -0.07
    uerdo
    -0.07
    veal
    -0.07
    ittel
    -0.07
    dbcTemplate
    -0.06
    orthand
    -0.06
    POSITIVE LOGITS
    åħ³
    0.06
    upa
    0.06
    ¦
    0.06
     tonnes
    0.05
     Birth
    0.05
    ANA
    0.05
     quan
    0.05
    æĤŁ
    0.05
    ìĿį
    0.05
     talk
    0.05
    Activations Density 0.029%

    No Known Activations