INDEX

Explanations

words that indicate significance or value in various 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

deo

-0.15

Ð¾Ð´Ð°

-0.15

urge

-0.15

$GLOBALS

-0.14

izen

-0.14

lush

-0.14

ughs

-0.14

owell

-0.14

Ð»Ð°ÑģÑĤÐ¸

-0.14

uw

-0.14

POSITIVE LOGITS

 enough

0.32

ly

0.23

 Enough

0.22

ness

0.20

ities

0.17

ITY

0.17

mente

0.17

lier

0.17

NESS

0.17

Enough

0.16

Activations Density 0.716%

words that indicate significance or value in various contexts

No Comments

No Known Activations