INDEX

Explanations

references to grenades or explosive devices

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Infinity

-0.16

curacy

-0.14

redi

-0.14

enko

-0.14

untu

-0.14

ua

-0.14

chap

-0.14

 Attribution

-0.13

anning

-0.13

ieg

-0.13

POSITIVE LOGITS

0.16

iaux

0.15

shal

0.15

ninger

0.14

ubber

0.14

.grp

0.14

.lesson

0.13

izona

0.13

iami

0.13

Activations Density 0.002%

references to grenades or explosive devices

No Comments

No Known Activations