INDEX

Explanations

phrases related to financial implications or costs

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

eki

-0.16

.available

-0.15

 universally

-0.14

OLID

-0.14

alom

-0.14

 Rich

-0.14

ÙĦÙĥ

-0.14

 inev

-0.14

oric

-0.13

esty

-0.13

POSITIVE LOGITS

 sensitive

0.21

 dependent

0.17

Sensitive

0.17

depend

0.17

QUIRES

0.17

dependent

0.16

 depend

0.16

 reliant

0.16

 delicate

0.16

 might

0.16

Activations Density 0.012%

phrases related to financial implications or costs

No Comments

No Known Activations