© 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. 90596
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and syntax used in document preparation

    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
    s
    -0.07
    ist
    -0.06
     per
    -0.06
     (
    -0.06
     notation
    -0.06
    er
    -0.05
    on
    -0.05
    a
    -0.05
    ks
    -0.05
    as
    -0.05
    POSITIVE LOGITS
     erotico
    0.10
    дап
    0.09
    uchos
    0.08
    ãģĮãģĦ
    0.08
    icari
    0.08
    .setViewport
    0.08
    esub
    0.08
     Barg
    0.08
    аÑĢÑĩ
    0.08
    PACE
    0.08
    Activations Density 0.055%

    No Known Activations