INDEX

Explanations

references to sellers and seller-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

zin

-0.19

illary

-0.17

ister

-0.16

aes

-0.16

áº£n

-0.15

unks

-0.15

ux

-0.14

zem

-0.14

á»§

-0.14

ole

-0.14

POSITIVE LOGITS

antro

0.17

 siden

0.16

 trÃŃ

0.15

insn

0.15

anzeigen

0.15

belt

0.15

rÅ¾

0.15

Ø§ÙĨØ³

0.14

tion

0.14

.Async

0.14

Activations Density 0.007%

references to sellers and seller-related terminology

No Comments

No Known Activations