INDEX

Explanations

expressions of gratitude and inquiries for help

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uell

-0.15

inst

-0.15

se

-0.14

Arb

-0.14

arence

-0.14

olume

-0.14

 miss

-0.14

 Cong

-0.13

 classic

-0.13

 Laden

-0.13

POSITIVE LOGITS

askell

0.17

jang

0.15

æ³ķ

0.14

Ð´Ð°Ð¿

0.14

bard

0.14

atern

0.13

.bpm

0.13

Attachments

0.13

ÄįÃ¡st

0.13

););↵

0.13

Activations Density 0.058%

expressions of gratitude and inquiries for help

No Comments

No Known Activations