INDEX

Explanations

elements related to academic discourse and structured arguments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ourcing

-0.15

ISO

-0.15

 Slim

-0.15

.hr

-0.15

 wholes

-0.14

Ran

-0.14

 sources

-0.14

lide

-0.13

POSITIVE LOGITS

 extensions

0.38

 extension

0.35

extension

0.31

extensions

0.31

 Extensions

0.30

 continuation

0.28

Extensions

0.28

 Extension

0.27

 derivative

0.27

Extension

0.26

Activations Density 0.237%

elements related to academic discourse and structured arguments

No Comments

No Known Activations