INDEX

Explanations

technical terms and their applications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

elor

-0.15

 authDomain

-0.15

 Ø¹Ø¯

-0.15

rzy

-0.14

ramer

-0.14

umbo

-0.14

Ú©Ø§Ø±ÛĮ

-0.14

olt

-0.14

roken

-0.14

POSITIVE LOGITS

Î¼ÎŃ

0.15

ulp

0.14

ãĥ¼ãĥ

0.14

TON

0.14

fit

0.14

ãģ£ãģ

0.14

å¥ª

0.14

zek

0.14

 htmlentities

0.14

èĬ

0.14

Activations Density 0.008%

technical terms and their applications in various contexts

No Comments

No Known Activations