INDEX

Explanations

comparative phrases highlighting differences or exceptions

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

ternet

-0.15

msp

-0.15

 Minor

-0.14

gii

-0.14

kus

-0.14

agrant

-0.14

 ******************************************************************************↵

-0.14

utut

-0.14

 AÄŁ

-0.14

-lfs

-0.14

POSITIVE LOGITS

º

0.15

berger

0.15

undle

0.15

lien

0.15

lian

0.14

atee

0.14

antar

0.14

uja

0.14

isko

0.14

ÐµÐ

0.14

Activations Density 0.036%

comparative phrases highlighting differences or exceptions

No Comments

No Known Activations