INDEX

Explanations

terms related to narratives involving conflict or dramatic circumstances

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

gi

-0.20

bab

-0.16

nell

-0.16

zzo

-0.16

ëĭ¤ê³ł

-0.15

Î¸Î±

-0.14

CACHE

-0.14

lil

-0.14

lia

-0.14

ifton

-0.14

POSITIVE LOGITS

stry

0.19

iflower

0.19

arella

0.18

ÏħÎ³

0.18

iliary

0.17

ê¸Ī

0.17

ÌĪ

0.17

ÌĨ

0.16

clide

0.15

ing

0.15

Activations Density 0.181%

terms related to narratives involving conflict or dramatic circumstances

No Known Activations