INDEX

Explanations

phrases and terms related to inclusion and compilation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

assin

-0.18

istrovstvÃŃ

-0.16

elerik

-0.15

ÙĩØ±

-0.15

REATED

-0.15

zan

-0.14

Ø§ÛĮØ´

-0.14

ibs

-0.14

ian

-0.13

olo

-0.13

POSITIVE LOGITS

/ex

0.18

erb

0.17

graphics

0.16

 cáº£

0.15

 both

0.15

aug

0.14

ERV

0.14

 ÑģÐ¾Ð±Ð¾Ð¹

0.14

ercial

0.13

Activations Density 0.053%

phrases and terms related to inclusion and compilation

No Comments

No Known Activations