INDEX

Explanations

instances of variable and data structure manipulations across different programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

amp

-0.15

à¸Ľà¸£à¸°à¹Ĥà¸¢à¸Ĭà¸Ļ

-0.14

Tier

-0.14

edik

-0.14

bon

-0.13

,readonly

-0.13

pcl

-0.13

.pc

-0.13

ãĥ¼ãĤ¯

-0.13

ÏħÏĥ

-0.13

POSITIVE LOGITS

readcr

0.15

 Ãľst

0.15

 Â¦

0.14

 Shades

0.14

oir

0.14

Ø§ÙģÙĬØ©

0.14

.getOwnProperty

0.14

ITHER

0.13

Fro

0.13

?action

0.13

Activations Density 0.097%

instances of variable and data structure manipulations across different programming contexts

No Comments

No Known Activations