INDEX

Explanations

negative constructions and conjunctions, indicating complex relationships and interactions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

empo

-0.16

zure

-0.14

Æ°Æ¡ng

-0.14

ikal

-0.14

anc

-0.14

Ð¹

-0.13

ablish

-0.13

 jinak

-0.13

IVAL

-0.13

ÑĤ

-0.13

POSITIVE LOGITS

0.17

illa

0.15

iar

0.15

åĴ²

0.14

-CS

0.14

ervo

0.14

yne

0.14

burgh

0.14

clr

0.13

CREMENT

0.13

Activations Density 0.001%

negative constructions and conjunctions, indicating complex relationships and interactions

No Known Activations