INDEX

Explanations

specific patterns related to documents and written content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.56

ÛĮ

-0.47

er

-0.46

ed

-0.42

-0.39

ing

-0.39

-0.38

Ø©

-0.38

-0.37

Ð¸

-0.35

POSITIVE LOGITS

imately

0.20

tempts

0.19

OwnProperty

0.18

stantiate

0.17

ServletRequest

0.17

ees

0.17

0.16

DebugEnabled

0.16

dependent

0.15

oe

0.15

Activations Density 0.936%

specific patterns related to documents and written content

No Comments

No Known Activations