INDEX

Explanations

instances of the word "earlier."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

yla

-0.18

 little

-0.16

sWith

-0.15

omet

-0.15

ritch

-0.14

boxes

-0.14

ses

-0.14

yl

-0.14

SES

-0.14

 older

-0.14

POSITIVE LOGITS

-than

0.37

_than

0.33

 than

0.32

 THAN

0.27

than

0.26

Than

0.23

 Than

0.22

_THAN

0.20

 neÅ¾

0.20

 Ð½ÑĸÐ¶

0.19

Activations Density 0.014%

instances of the word "earlier."

No Comments

No Known Activations