INDEX

Explanations

phrases that express contrast or contradiction

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

erland

-0.15

 suppose

-0.15

erb

-0.14

èĻ½çĦ¶

-0.14

itest

-0.14

burg

-0.14

 though

-0.14

erte

-0.13

 guess

-0.13

bine

-0.13

POSITIVE LOGITS

chers

0.25

ting

0.18

ler

0.18

thead

0.17

ÑģÑıÑĤ

0.17

ts

0.17

ted

0.16

ters

0.14

LER

0.14

 also

0.14

Activations Density 0.111%

phrases that express contrast or contradiction

No Comments

No Known Activations