INDEX

Explanations

references to payment or compensation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

atÃ³

-0.15

 accumulation

-0.15

 balance

-0.14

front

-0.14

.viewport

-0.14

uby

-0.13

ilingual

-0.13

qb

-0.13

POSITIVE LOGITS

ocu

0.15

iddy

0.15

Ø§Ø¯ÙĨ

0.15

IFIC

0.14

ÐµÐ³Ð°

0.14

Doctrine

0.14

è·

0.14

doctrine

0.14

hPa

0.14

Activations Density 0.031%

references to payment or compensation in various contexts

No Comments

No Known Activations