INDEX

Explanations

numerical references, particularly dates and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

emm

-0.15

 refrain

-0.14

ecute

-0.14

IntArray

-0.14

 Morrow

-0.14

 finger

-0.14

lek

-0.14

ocket

-0.13

-unstyled

-0.13

semble

-0.13

POSITIVE LOGITS

emean

0.17

undry

0.15

åģ¥

0.14

.opensource

0.14

stab

0.14

ÙĤØ§Ùħ

0.13

lÄ±ÄŁÄ±nÄ±n

0.13

oub

0.13

Äı

0.13

Activations Density 0.038%

numerical references, particularly dates and statistics

No Comments

No Known Activations