INDEX

Explanations

mentions of systemic failures and governmental negligence

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

/goto

-0.15

ietf

-0.14

.iOS

-0.14

irim

-0.14

Forbidden

-0.13

æ¯Ľ

-0.13

ÏĦÎ¿

-0.13

 STRICT

-0.13

Interrupt

-0.13

trainer

-0.12

POSITIVE LOGITS

 failures

0.33

 failure

0.33

 fail

0.29

 failed

0.29

 Fail

0.28

failure

0.28

 Failure

0.27

fail

0.26

 failing

0.26

 Failed

0.25

Activations Density 0.215%

mentions of systemic failures and governmental negligence

No Comments

No Known Activations