INDEX

Explanations

instances of the word "Over" with varying frequencies, indicating a focus on repetition and emphasis 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

odÄĽ

-0.16

inalg

-0.15

åĭ¢

-0.15

owie

-0.14

aland

-0.14

ullo

-0.14

virt

-0.13

ÑĢÐ°Ð¿

-0.13

owi

-0.13

owitz

-0.13

POSITIVE LOGITS

edList

0.15

ATIO

0.15

łĢ

0.14

heard

0.14

Mb

0.14

ãĤ¤ãĥĦ

0.14

ph

0.14

aney

0.14

ader

0.13

Activations Density 0.015%

instances of the word "Over" with varying frequencies, indicating a focus on repetition and emphasis in the text

No Comments

No Known Activations