INDEX

Explanations

specific times mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

hots

-0.16

/Typography

-0.15

YST

-0.15

 ç¸

-0.14

Ø§ÙĩÛĮ

-0.14

 Accident

-0.14

ighth

-0.14

iras

-0.14

ongo

-0.14

iamond

-0.14

POSITIVE LOGITS

 Hammond

0.16

rolls

0.15

èªĮ

0.14

otify

0.14

arning

0.14

DNS

0.14

ksam

0.14

 KeyCode

0.14

 dawn

0.14

Activations Density 0.061%

specific times mentioned in the text

No Comments

No Known Activations