INDEX

Explanations

terms related to financial and insurance concepts, particularly involving funds and policies

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

tuk

-0.17

moz

-0.15

ÑģÑĤÑĢÐ°

-0.14

 ç¢

-0.14

.FC

-0.14

æŁ³

-0.14

æĥĳ

-0.14

Ð²Ð°Ð»Ð¸

-0.14

Hun

-0.14

å©

-0.14

POSITIVE LOGITS

 Kendrick

0.15

Fir

0.15

 Berm

0.14

BB

0.14

fir

0.14

ISIBLE

0.14

PP

0.13

 fossil

0.13

ibling

0.13

Activations Density 0.080%

terms related to financial and insurance concepts, particularly involving funds and policies

No Comments

No Known Activations