INDEX

Explanations

the word "one" and its variations, indicating a focus on singularity or emphasis on individual instances

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

atile

-0.14

pliers

-0.13

TRL

-0.13

/from

-0.13

 Prefer

-0.13

 ÑģÐ¾Ð±Ñĸ

-0.12

piler

-0.12

ched

-0.12

-Identifier

-0.12

dle

-0.12

POSITIVE LOGITS

 advantage

0.23

of

0.22

 such

0.22

 consequence

0.21

 benefit

0.21

 reason

0.21

 thing

0.20

 drawback

0.20

 difficulty

0.20

 wonders

0.20

Activations Density 0.058%

the word "one" and its variations, indicating a focus on singularity or emphasis on individual instances

No Comments

No Known Activations