© 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. 22-LLAMASCOPE-RES-32K
    11. 10574
    Prev
    Next
    INDEX
    Explanations

    specific words related to art and its preservation, including terms associated with visual aesthetics and artistic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤŃãĥ¥
    -0.16
     плоÑī
    -0.15
    ifestyles
    -0.14
    redient
    -0.14
     Lars
    -0.14
    571
    -0.14
    aina
    -0.14
    indle
    -0.14
    emark
    -0.14
    .serializer
    -0.13
    POSITIVE LOGITS
     вÑĢемÑı
    0.22
     колиÑĩеÑģÑĤво
    0.19
     дело
    0.17
     ÑģÑĢедÑģÑĤво
    0.17
     ÑĢаÑģÑĤение
    0.17
     знаÑĩение
    0.17
    ождение
    0.17
    иÑĤелÑĮное
    0.16
    Ïīμα
    0.16
     знаÑĩеннÑı
    0.16
    Activations Density 0.030%

    No Known Activations