INDEX

Explanations

instances of the word "and" indicating connections or additions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

iol

-0.16

alles

-0.16

vant

-0.15

ëĿ½

-0.15

anko

-0.14

éĽ¢

-0.14

(*(

-0.14

ÐĴÐŀ

-0.14

chemy

-0.13

eteor

-0.13

POSITIVE LOGITS

orm

0.14

 shift

0.14

 disc

0.14

ãģ«ãģ¨

0.13

vis

0.13

aklÄ±

0.13

Â¸

0.13

Activations Density 0.304%

instances of the word "and" indicating connections or additions in the text

No Comments

No Known Activations