INDEX

Explanations

textual references to risks, challenges, and safety concerns 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

inet

-0.18

iner

-0.17

prÃ¼

-0.16

acci

-0.15

loth

-0.15

otch

-0.15

orgen

-0.14

 PÃ©

-0.14

asc

-0.14

ici

-0.14

POSITIVE LOGITS

 when

0.31

khi

0.26

 quando

0.25

when

0.25

When

0.22

	when

0.21

 When

0.21

 cuando

0.20

 WHEN

0.19

 lorsque

0.18

Activations Density 0.299%

textual references to risks, challenges, and safety concerns in various contexts

No Comments

No Known Activations