INDEX

Explanations

references to specific locations or names associated with the Korean context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iske

-0.16

 inflate

-0.15

apro

-0.14

 inflated

-0.14

flt

-0.14

 Fuse

-0.14

Closure

-0.13

amping

-0.13

omp

-0.13

.Speed

-0.13

POSITIVE LOGITS

¹

0.14

Ø§ÙĨÛĮ

0.14

riger

0.14

Ã¡l

0.14

azo

0.14

nia

0.13

.qq

0.13

adro

0.13

jar

0.13

craft

0.13

Activations Density 0.018%

references to specific locations or names associated with the Korean context

No Comments

No Known Activations