INDEX

Explanations

phrases indicating approximations or estimates in numerical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lein

-0.17

 Ones

-0.16

utdown

-0.15

 Exactly

-0.15

 exactly

-0.15

Î»Ïī

-0.14

 Heck

-0.14

 ones

-0.14

pector

-0.14

courses

-0.14

POSITIVE LOGITS

LY

0.14

ãĤ±ãĥĥãĥĪ

0.14

 twice

0.13

-ÑĤÐ°ÐºÐ¸

0.13

ê°Ħ

0.13

amat

0.13

 dozen

0.13

inis

0.13

Activations Density 0.107%

phrases indicating approximations or estimates in numerical contexts

No Comments

No Known Activations