INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

wan

-0.15

hoe

-0.14

 Carly

-0.14

voy

-0.14

è«ĸ

-0.14

adaki

-0.13

wand

-0.13

/includes

-0.13

 ì¤

-0.13

 Insets

-0.13

POSITIVE LOGITS

igne

0.18

ownt

0.16

uxt

0.15

OMIC

0.15

rosse

0.15

ãĤ¹ãĤ³

0.15

elize

0.15

0.14

PLICATE

0.14

mer

0.14

Activations Density 0.008%

expressions of gratitude and appreciation

No Comments

No Known Activations