INDEX

Explanations

references to investigations and inquiries into various cases and incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

sik

-0.16

å¤

-0.14

è°±

-0.14

chner

-0.13

ylon

-0.13

à¸ĩà¹ģà¸ķ

-0.13

ÐµÑĩ

-0.13

oldt

-0.13

ulses

-0.13

Ð²ÐµÑģÑĤÐ¸

-0.13

POSITIVE LOGITS

 into

0.52

into

0.45

 Into

0.41

 INTO

0.37

Into

0.36

_into

0.35

.into

0.27

 probing

0.26

 conducted

0.26

 looking

0.24

Activations Density 0.052%

references to investigations and inquiries into various cases and incidents

No Comments

No Known Activations