INDEX

Explanations

references to umbrellas or related terms

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

liner

-0.16

leo

-0.16

divider

-0.16

¿Ĳ

-0.15

thon

-0.15

ISIBLE

-0.15

 MetroFramework

-0.15

ptal

-0.15

.lwjgl

-0.15

piler

-0.15

POSITIVE LOGITS

Umb

0.32

umb

0.29

rella

0.28

rellas

0.28

umb

0.27

 umbrella

0.22

il

0.19

riel

0.19

lical

0.18

rell

0.18

Activations Density 0.007%

references to umbrellas or related terms

No Comments

No Known Activations

references to umbrellas or related terms

No Comments

No Known Activations