INDEX

Explanations

the word "told" and its variations, indicating information-sharing or communication

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

eteria

-0.17

dic

-0.17

Ã´n

-0.15

Ø

-0.15

 ongoing

-0.14

Î¯Î³

-0.14

azer

-0.14

dere

-0.14

etine

-0.13

POSITIVE LOGITS

zim

0.16

ĺħ

0.15

orian

0.15

exion

0.15

Ø§ÙĪÙĨØ¯

0.15

id

0.14

AVA

0.14

cky

0.13

robots

0.13

berger

0.13

Activations Density 0.018%

the word "told" and its variations, indicating information-sharing or communication

No Comments

No Known Activations