INDEX

Explanations

phrases related to supplemental content or additional information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ane

-0.15

ANE

-0.15

bau

-0.15

chner

-0.14

andr

-0.14

xn

-0.14

rud

-0.14

ãĢģæĹ¥æľ¬

-0.13

ope

-0.13

 Wand

-0.13

POSITIVE LOGITS

dge

0.16

leton

0.16

elow

0.14

 ÑģÐ²ÐµÑĢ

0.13

licted

0.13

 Wikimedia

0.13

vez

0.13

 Ð¿ÑĢÐ¾Ñĩ

0.13

oleÄį

0.13

Activations Density 0.011%

phrases related to supplemental content or additional information

No Comments

No Known Activations