INDEX

Explanations

elements associated with durations or time periods in content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

agem

-0.15

bro

-0.15

 wards

-0.15

 spot

-0.15

loon

-0.14

 swing

-0.14

udden

-0.14

ãĤħ

-0.14

POSITIVE LOGITS

eniable

0.18

ÑĥÑĢÑģ

0.15

wner

0.15

ç§ĳæĬĢæľīéĻĲåħ¬åı¸

0.14

/repos

0.14

æķ¦

0.14

ynchronized

0.14

filme

0.14

assi

0.14

stroy

0.13

Activations Density 0.011%

elements associated with durations or time periods in content

No Comments

No Known Activations