INDEX

Explanations

intensity or emphasis in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

oot

-0.16

ÏĢÎ¿Î¹Î·

-0.15

cape

-0.15

dat

-0.14

antine

-0.14

Tac

-0.14

-Ta

-0.14

emm

-0.14

Vig

-0.14

 Ying

-0.14

POSITIVE LOGITS

alte

0.20

ampa

0.17

alu

0.16

 roller

0.15

xima

0.14

auge

0.14

sher

0.14

ãģıãĤĮ

0.14

bie

0.14

.DropTable

0.14

Activations Density 0.014%

intensity or emphasis in statements

No Comments

No Known Activations