INDEX

Explanations

instances of the word "pair" and its variations, indicating a focus on partnerships or collaborations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

pany

-0.18

ä¸īçº§

-0.17

edir

-0.16

eti

-0.16

aries

-0.15

rud

-0.15

/ion

-0.15

ãĥ³ãĥĲ

-0.15

Ð¾Ð¼ÐµÑĢ

-0.15

Ð½Ð°ÑĢ

-0.15

POSITIVE LOGITS

ings

0.40

INGS

0.28

/group

0.26

tures

0.23

wise

0.21

/groups

0.21

/single

0.19

-wise

0.19

ä¼į

0.18

rr

0.18

Activations Density 0.027%

instances of the word "pair" and its variations, indicating a focus on partnerships or collaborations

No Comments

No Known Activations