INDEX

Explanations

questions about the creators and details of animated shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

zend

-0.17

ily

-0.16

ScreenState

-0.15

chied

-0.14

quan

-0.14

Îº

-0.14

EB

-0.14

íģ

-0.14

plr

-0.14

privileged

-0.13

POSITIVE LOGITS

TickCount

0.16

Bek

0.16

untu

0.15

 æĻ

0.14

rif

0.14

obus

0.14

å®¾

0.14

bable

0.14

Jew

0.14

UMAN

0.14

Activations Density 0.118%

questions about the creators and details of animated shows

No Comments

No Known Activations