© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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-32K
    11. 5245
    Prev
    Next
    INDEX
    Explanations

    references to movies and their elements, particularly titles and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    202
    -0.33
     Tik
    -0.28
     COVID
    -0.26
     Covid
    -0.24
     covid
    -0.24
     Biden
    -0.24
    Û²Û°Û²
    -0.23
     SwiftUI
    -0.23
     pandemic
    -0.22
     bush
    -0.21
    POSITIVE LOGITS
     Zika
    0.30
    201
    0.29
     âĢª
    0.27
     Hollande
    0.24
     tumblr
    0.22
     xrange
    0.21
     ISIS
    0.21
    goo
    0.21
    Û²Û°Û±
    0.20
    #.
    0.20
    Activations Density 0.409%

    No Known Activations