INDEX

Explanations

mathematical notations or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

luv

-0.17

elu

-0.16

yne

-0.15

Zug

-0.15

Ã±ana

-0.15

artz

-0.14

.rmi

-0.14

udded

-0.14

esda

-0.14

oot

-0.14

POSITIVE LOGITS

ei

0.14

 scar

0.14

cit

0.14

_REF

0.14

/goto

0.14

ifar

0.13

 Chunk

0.13

è³¢

0.13

et

0.13

em

0.13

Activations Density 0.027%

mathematical notations or symbols

No Comments

No Known Activations