INDEX

Explanations

phrases that indicate increase or rise in contexts related to inequality or disparity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÑģÐ¾Ð½

-0.15

mars

-0.14

ÑĮ

-0.14

anka

-0.14

 PartialView

-0.14

 Leer

-0.14

eurs

-0.14

ibur

-0.14

Nx

-0.14

NA

-0.13

POSITIVE LOGITS

Ary

0.16

Ð½Ð¾ÑģÐ¸

0.15

pron

0.15

loh

0.15

 McCoy

0.14

assi

0.14

ibling

0.14

fÃ¼h

0.14

auge

0.14

ins

0.13

Activations Density 0.018%

phrases that indicate increase or rise in contexts related to inequality or disparity

No Comments

No Known Activations