Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 23133
    Prev
    Next
    INDEX
    Explanations

    technical references related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eli
    -0.15
     <-
    -0.15
    UBE
    -0.15
    [
    -0.15
     =
    -0.14
    ¹Ħ
    -0.14
    виÑĩ
    -0.14
    .xz
    -0.14
     Devon
    -0.14
     Homework
    -0.13
    POSITIVE LOGITS
    .h
    0.36
    .hpp
    0.26
     header
    0.23
    .cpp
    0.22
    .pb
    0.22
    _INCLUDED
    0.21
    .inc
    0.21
    /include
    0.19
    Defines
    0.19
    include
    0.19
    Activations Density 0.029%

    No Known Activations