INDEX

Explanations

variable declarations and assignments in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

inho

-0.13

ovÃ¡

-0.13

->$

-0.13

eltas

-0.12

avan

-0.12

ÅŁk

-0.12

ised

-0.12

å¼¥

-0.12

auer

-0.12

owski

-0.12

POSITIVE LOGITS

urf

0.15

istrovstvÃŃ

0.15

.TryParse

0.14

stery

0.13

 Mahm

0.13

oline

0.13

eck

0.13

ploy

0.13

URN

0.12

(?:

0.12

Activations Density 0.183%

variable declarations and assignments in code

No Comments

No Known Activations