INDEX

Explanations

terms and expressions related to names or entities that signify resistance or opposition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ICC

-0.26

McC

-0.25

GCC

-0.24

Abb

-0.23

 Abbott

-0.23

ICC

-0.23

MCC

-0.22

 McCorm

-0.22

gcc

-0.22

McC

-0.21

POSITIVE LOGITS

à©

0.20

ãĥĥ

0.19

tte

0.19

alles

0.18

alle

0.17

alley

0.17

Î»Î»Î±

0.17

ÐµÐ½Ð½Ð¾Ð¼

0.16

anne

0.16

allest

0.16

Activations Density 0.030%

terms and expressions related to names or entities that signify resistance or opposition

No Comments

No Known Activations