INDEX

Explanations

terms related to "shock" or "shocking" experiences or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

fty

-0.18

Ð¸ÑģÐº

-0.16

stvo

-0.15

nty

-0.15

ighth

-0.15

esa

-0.14

ÐºÐ¸Ð½

-0.14

une

-0.14

iac

-0.14

ÑģÑıÑĩ

-0.14

POSITIVE LOGITS

ingly

0.45

wave

0.32

waves

0.30

 absor

0.27

tober

0.27

 waves

0.23

Wave

0.20

 wave

0.19

ument

0.19

ively

0.18

Activations Density 0.014%

terms related to "shock" or "shocking" experiences or concepts

No Comments

No Known Activations