INDEX

Explanations

punctuation marks and their associated contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 cÅ©ng

-0.14

EGA

-0.13

 McDon

-0.13

oglobin

-0.13

kor

-0.13

ãģĳãĤĮãģ°

-0.13

ET

-0.12

.enterprise

-0.12

 Larson

-0.12

istant

-0.12

POSITIVE LOGITS

how

0.30

why

0.26

How

0.22

how

0.20

How

0.18

 cÃ³mo

0.18

-how

0.17

Why

0.17

 reasons

0.16

ystack

0.16

Activations Density 0.059%

punctuation marks and their associated contexts

No Comments

No Known Activations