INDEX

Explanations

terms associated with violent incidents and fatalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ewis

-0.16

ardi

-0.15

alars

-0.14

heim

-0.14

.expect

-0.14

 cred

-0.14

Ð¼ÐµÑĢÐ¸Ðº

-0.14

ãĤıãģĽ

-0.14

Ð»Ð¾ÑĤ

-0.14

Ð»Ð°Ð´Ð°

-0.14

POSITIVE LOGITS

PEND

0.16

 tackling

0.14

trak

0.14

istical

0.14

ergy

0.14

bsd

0.14

egral

0.13

orary

0.13

 padd

0.13

Activations Density 0.052%

terms associated with violent incidents and fatalities

No Comments

No Known Activations