INDEX

Explanations

concepts related to ergonomics and workplace efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ÑĢÐ¾Ð¹

-0.15

iffin

-0.15

_subtype

-0.14

 åı¸

-0.14

 dish

-0.14

ifes

-0.14

 Ø¢Ø°

-0.14

IFA

-0.14

Ø§Ø¬

-0.13

.dtd

-0.13

POSITIVE LOGITS

 Lean

0.36

 lean

0.32

Lean

0.29

lean

0.28

LEAN

0.26

Gem

0.26

 improvement

0.25

Six

0.25

 Improvement

0.25

ka

0.25

Activations Density 0.026%

concepts related to ergonomics and workplace efficiency

No Comments

No Known Activations