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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23212
    Prev
    Next
    INDEX
    Explanations

    concepts related to programming and algorithmic functions

    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
    affles
    -0.16
    ανά
    -0.15
     screening
    -0.15
    arie
    -0.14
     поÑģÑĤанов
    -0.14
    sted
    -0.14
     backlight
    -0.14
    gallery
    -0.14
    å½±
    -0.14
    Printf
    -0.14
    POSITIVE LOGITS
     patch
    0.27
    patch
    0.27
    Patch
    0.26
    _patch
    0.26
     Patch
    0.25
     pitch
    0.25
     Pitch
    0.25
     pitches
    0.24
     patches
    0.24
    PATCH
    0.23
    Activations Density 0.006%

    No Known Activations