INDEX

Explanations

instances of the word "each" and related terms indicating distribution or individual items in a set

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

amen

-0.17

igan

-0.15

iverse

-0.15

iw

-0.15

less

-0.14

 eigen

-0.13

 possessions

-0.13

 resources

-0.13

ric

-0.13

Meh

-0.13

POSITIVE LOGITS

each

0.18

 respective

0.18

(each

0.16

 each

0.16

ê°ģ

0.15

ãĥ³ãĥĳ

0.15

ergy

0.15

ebek

0.15

Each

0.14

 ÐºÐ°Ð¶Ð´Ð¾Ð³Ð¾

0.14

Activations Density 0.058%

instances of the word "each" and related terms indicating distribution or individual items in a set

No Comments

No Known Activations