INDEX

Explanations

keywords and symbols that indicate code structure and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

pard

-0.15

Ã§e

-0.15

ernes

-0.14

Äĵ

-0.14

 cheers

-0.14

.kr

-0.14

 Sick

-0.14

ed

-0.13

Author

-0.13

mn

-0.13

POSITIVE LOGITS

Wunused

0.16

elt

0.16

 Brock

0.15

mony

0.15

ieber

0.14

ITTE

0.14

aldo

0.14

REE

0.14

ì¶ľ

0.14

ÏĥÎ¼

0.13

Activations Density 0.063%

keywords and symbols that indicate code structure and function definitions

No Comments

No Known Activations