INDEX

Explanations

pronouns, particularly variations of "it."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.ba

-0.17

rette

-0.15

stype

-0.15

illas

-0.15

|_|

-0.14

 Warning

-0.14

acos

-0.14

ITTE

-0.13

Fet

-0.13

duc

-0.13

POSITIVE LOGITS

thood

0.17

Î¼Î¹

0.14

keit

0.14

á»Ĩ

0.14

à¸²à¸ķà¸£

0.14

tpl

0.14

addr

0.13

Ø±ÙĪÛĮ

0.13

 Ipsum

0.13

Unt

0.13

Activations Density 0.047%

pronouns, particularly variations of "it."

No Comments

No Known Activations