INDEX

Explanations

phrases indicating belief or conviction

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ãĥ³ãĥĨãĤ£

-0.18

resh

-0.17

igo

-0.16

hof

-0.14

aq

-0.14

Ã«r

-0.14

 Stern

-0.14

plements

-0.14

£p

-0.14

chin

-0.13

POSITIVE LOGITS

atatype

0.18

0.15

autÃ©

0.14

chema

0.14

adro

0.14

0.13

difference

0.13

å·®

0.13

LOB

0.13

Activations Density 0.024%

phrases indicating belief or conviction

No Comments

No Known Activations