INDEX

Explanations

phrases that introduce or qualify statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 jednak

-0.16

wd

-0.15

chemes

-0.15

ÑģÑĤÐ²Ð¾

-0.14

ney

-0.14

'&&

-0.14

 Either

-0.14

uous

-0.13

iph

-0.13

force

-0.13

POSITIVE LOGITS

 importantly

0.23

 later

0.20

 lately

0.17

 optionally

0.16

 surtout

0.16

į¼

0.16

nty

0.15

 evet

0.15

 subsequently

0.15

REW

0.15

Activations Density 0.036%

phrases that introduce or qualify statements

No Comments

No Known Activations