INDEX

Explanations

temporal references related to historical or ongoing events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

eux

-0.18

him

-0.17

SizeMode

-0.16

 Ð½ÑĮÐ¾Ð³Ð¾

-0.16

æĺ¯æĪĳ

-0.15

them

-0.15

 whom

-0.14

CharacterSet

-0.14

lui

-0.13

esser

-0.13

POSITIVE LOGITS

 there

0.35

there

0.28

we

0.24

it

0.23

 ÙģØ¥ÙĨ

0.23

 they

0.22

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.21

 thÃ¬

0.20

we

0.19

Activations Density 0.291%

temporal references related to historical or ongoing events

No Comments

No Known Activations