INDEX

Explanations

phrases that indicate balance or equilibrium in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lus

-0.17

lg

-0.15

lis

-0.14

/html

-0.14

å£ģ

-0.14

elligent

-0.14

iya

-0.14

Wol

-0.13

ches

-0.13

POSITIVE LOGITS

balance

0.20

adro

0.17

(balance

0.17

-bal

0.17

 balance

0.17

 Balance

0.16

OfString

0.15

$MESS

0.15

ä¼į

0.15

aland

0.14

Activations Density 0.035%

phrases that indicate balance or equilibrium in various contexts

No Comments

No Known Activations