INDEX

Explanations

elements related to idyllic and picturesque settings or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ag

-0.17

unga

-0.16

 Zero

-0.15

ilon

-0.15

(*.

-0.14

à¤¾à¤¸à¤¨

-0.14

utherford

-0.14

ă

-0.13

EZ

-0.13

 Barr

-0.13

POSITIVE LOGITS

iew

0.15

Å¡ov

0.15

 retirement

0.14

uÅŁ

0.14

ifique

0.14

 Nice

0.14

ç¥¥

0.14

ulas

0.14

izoph

0.14

orno

0.14

Activations Density 0.238%

elements related to idyllic and picturesque settings or experiences

No Comments

No Known Activations