INDEX

Explanations

constructs and references related to data structures and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

znik

-0.15

nez

-0.15

ãĥĥãĤ·ãĥ¥

-0.15

abet

-0.14

_tA

-0.14

xBB

-0.14

Scoped

-0.14

obsolete

-0.14

richt

-0.14

ç°

-0.13

POSITIVE LOGITS

 empty

0.33

 blank

0.30

 Empty

0.29

 dummy

0.28

 Null

0.28

 null

0.28

empty

0.27

-empty

0.26

Empty

0.26

ç©º

0.26

Activations Density 0.235%

constructs and references related to data structures and programming concepts

No Comments

No Known Activations