INDEX

Explanations

phrases related to increases or improvements in financial or quantitative metrics

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

Buf

-0.18

INLINE

-0.15

åŃĿ

-0.15

AYOUT

-0.14

stalk

-0.14

ÑıÑħ

-0.14

heit

-0.14

hart

-0.14

Ø§ÙĨÙĩ

-0.14

.Fat

-0.14

POSITIVE LOGITS

batis

0.17

 chance

0.15

iles

0.14

 edin

0.14

á»Ļc

0.14

isher

0.14

ENDING

0.13

 Alle

0.13

+i

0.13

 ALOG

0.13

Activations Density 0.165%

phrases related to increases or improvements in financial or quantitative metrics

No Comments

No Known Activations