INDEX

Explanations

references to data types and structures used in programming

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

name

-0.17

enthal

-0.16

side

-0.15

 trÃŃ

-0.15

iar

-0.15

dess

-0.15

ãĥ¼ãĤ¸

-0.15

sing

-0.15

gregar

-0.14

time

-0.14

POSITIVE LOGITS

osate

0.17

atsu

0.16

umin

0.16

gua

0.16

guns

0.15

alÄ±k

0.14

Ð¾Ð¿Ð¸Ñģ

0.14

ÐµÐ·Ð´Ð°

0.14

/terms

0.14

 ÎĶÎ¹Î±

0.14

Activations Density 0.035%

references to data types and structures used in programming

No Comments

No Known Activations