© 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-32K
    11. 22313
    Prev
    Next
    INDEX
    Explanations

    elements related to administrative or operational processes and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aber
    -0.15
     ç¦ı
    -0.14
    inst
    -0.14
    ør
    -0.14
    of
    -0.13
     Fifty
    -0.13
    stdarg
    -0.13
     Rudy
    -0.13
    remium
    -0.13
    iko
    -0.13
    POSITIVE LOGITS
    eview
    0.17
    .Apis
    0.16
    .IContainer
    0.15
     JMP
    0.15
     DISCLAIM
    0.15
    iquer
    0.14
    GREE
    0.14
    اشÛĮÙĨ
    0.14
    ัà¸ļà¸ģาร
    0.13
    νοÏį
    0.13
    Activations Density 0.531%

    No Known Activations