INDEX

Explanations

various connecting words and phrases that signify logical relationships in academic or analytical writing

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

 corner

-0.16

mium

-0.14

 stead

-0.14

woo

-0.14

Ã¶n

-0.14

MMC

-0.14

 crystal

-0.14

ÃŁ

-0.13

sed

-0.13

POSITIVE LOGITS

ÐºÐ¾ÑĤ

0.15

ÐºÐ¾Ð²Ð¾Ð¹

0.15

áº£nh

0.15

xec

0.15

agrant

0.14

idge

0.14

ibar

0.14

èĴ

0.14

ulta

0.14

agne

0.13

Activations Density 0.001%

various connecting words and phrases that signify logical relationships in academic or analytical writing

No Comments

No Known Activations