INDEX

Explanations

code-related terms and expressions, particularly those dealing with conditions and declarations in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Virgin

-0.19

 Virgin

-0.17

.scalar

-0.15

vir

-0.15

inha

-0.15

unge

-0.15

ilon

-0.14

_attached

-0.14

ungs

-0.14

iner

-0.14

POSITIVE LOGITS

posta

0.14

ACK

0.14

AndView

0.13

 sequence

0.13

SEQ

0.13

Rai

0.13

 copp

0.13

Ã©mon

0.13

/env

0.13

 Bros

0.13

Activations Density 0.183%

code-related terms and expressions, particularly those dealing with conditions and declarations in programming

No Comments

No Known Activations

code-related terms and expressions, particularly those dealing with conditions and declarations in programming

No Comments

No Known Activations