INDEX

Explanations

important dates or numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Gret

-0.16

Ì£

-0.16

çīĩ

-0.15

spin

-0.14

å¼ķãģį

-0.13

reeze

-0.13

cox

-0.13

mt

-0.13

inesis

-0.13

Ä©

-0.13

POSITIVE LOGITS

OrNil

0.14

iman

0.14

/posts

0.14

dy

0.13

ãĥ¼ãĥ«ãĥī

0.13

_errors

0.13

tatus

0.13

.scalablytyped

0.13

gorm

0.13

igon

0.12

Activations Density 0.017%

important dates or numerical values

No Comments

No Known Activations