INDEX

Explanations

code-related elements and structures within a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Lazy

-0.14

ihan

-0.14

çĽĺ

-0.14

 Wend

-0.14

Buf

-0.14

ither

-0.14

 lazy

-0.13

erview

-0.13

_ASM

-0.13

inf

-0.13

POSITIVE LOGITS

.timestamps

0.25

timestamps

0.25

 indexes

0.19

foreign

0.18

 foreign

0.18

orp

0.17

 column

0.16

 timestamps

0.16

 FOREIGN

0.16

 Column

0.16

Activations Density 0.004%

code-related elements and structures within a programming context

No Comments

No Known Activations