INDEX

Explanations

code-related keywords and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Moody

-0.16

Zuk

-0.16

-0.15

lyn

-0.14

printStats

-0.14

uetype

-0.14

 åī

-0.14

ÃŃrk

-0.13

POSITIVE LOGITS

alem

0.15

_EV

0.15

Å¯v

0.14

Ø¨Ø§Ø±

0.14

Ð±Ð¸Ð½Ð°

0.14

ButtonType

0.14

å¸¯

0.14

 æ¥Ń

0.14

sville

0.14

êµ°

0.14

Activations Density 0.042%

code-related keywords and functions

No Comments

No Known Activations