INDEX

Explanations

references to events or gatherings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Raphael

-0.17

tras

-0.16

ptions

-0.16

ausal

-0.16

iae

-0.15

ico

-0.14

 æ¢

-0.14

iaux

-0.14

plits

-0.14

 Morg

-0.14

POSITIVE LOGITS

Nos

0.16

LocalizedString

0.15

HTTPHeader

0.15

Ð¾Ð¼Ñĸ

0.15

olla

0.15

Calibri

0.14

ella

0.14

Ã¥de

0.14

uin

0.14

_NT

0.14

Activations Density 1.173%

references to events or gatherings

No Comments

No Known Activations