INDEX

Explanations

repeated phrases and recurring references in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-0.15

hel

-0.15

Hel

-0.15

opoulos

-0.14

ju

-0.14

vit

-0.14

 Letter

-0.14

 ransom

-0.14

 letter

-0.14

↵

-0.14

POSITIVE LOGITS

arshal

0.19

osaur

0.19

@nate

0.15

 Ð·Ð°Ð²Ð¸

0.14

ertz

0.14

arah

0.14

Å¡Å¥

0.14

Ã©ra

0.14

onomy

0.14

desired

0.14

Activations Density 0.051%

repeated phrases and recurring references in a document

No Comments

No Known Activations