INDEX

Explanations

instances of the word "or" and its variations

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

istik

-0.17

 Ballard

-0.16

iddle

-0.15

ilm

-0.15

astes

-0.14

 Äįin

-0.14

wagon

-0.14

amt

-0.14

bara

-0.14

ifact

-0.14

POSITIVE LOGITS

eners

0.15

phans

0.15

rary

0.14

odic

0.14

ÑıÑĤÐ¸Ñı

0.14

Ð¢Ð°

0.14

.REG

0.14

 Dolphin

0.14

 rede

0.13

Ú¯ÛĮØ±ÛĮ

0.13

Activations Density 0.109%

instances of the word "or" and its variations

No Comments

No Known Activations