INDEX

Explanations

phrases indicating repetition or continuity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

och

-0.17

 Twice

-0.16

ÌĤ

-0.15

ister

-0.15

rell

-0.14

ISTER

-0.14

ìĹ

-0.13

 Nova

-0.13

 ÐºÐ»Ð¸

-0.13

POSITIVE LOGITS

bai

0.21

Å¡en

0.16

aeper

0.16

à¹Ģà¸«à¸¥

0.16

pio

0.15

.ease

0.15

SION

0.15

ÑĪÐ¸Ð±

0.15

hai

0.15

oval

0.15

Activations Density 0.155%

phrases indicating repetition or continuity

No Comments

No Known Activations