INDEX

Explanations

expressions of uncertainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Probably

-0.17

 zÅĻejmÄĽ

-0.15

 probably

-0.15

 Apparently

-0.15

probably

-0.15

 muht

-0.15

 reportedly

-0.15

 Basically

-0.14

 Ð¾Ð±ÑĭÑĩÐ½Ð¾

-0.14

licer

-0.14

POSITIVE LOGITS

 even

0.26

 because

0.22

 none

0.22

 some

0.22

not

0.22

it

0.21

 something

0.20

 someone

0.20

 more

0.19

 they

0.19

Activations Density 0.055%

expressions of uncertainty or speculation

No Comments

No Known Activations