INDEX

Explanations

phrases that express evaluations or opinions on quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 cred

-0.19

decor

-0.15

 instead

-0.14

xcf

-0.14

Bay

-0.14

Ì

-0.14

 concrete

-0.14

 tiáº¿t

-0.14

 adip

-0.14

 Rash

-0.14

POSITIVE LOGITS

arella

0.16

isky

0.16

allback

0.16

cpy

0.15

indr

0.15

avaÅŁ

0.15

enth

0.15

endif

0.14

 Tits

0.14

igu

0.14

Activations Density 0.196%

phrases that express evaluations or opinions on quality

No Comments

No Known Activations