INDEX

Explanations

language related to conflict and strong emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

à¸Ńà¸¢

-0.16

paged

-0.16

istro

-0.15

 Vivo

-0.14

Ops

-0.14

[sizeof

-0.14

kara

-0.14

Ã©is

-0.14

ining

-0.14

POSITIVE LOGITS

ta

0.44

0.41

0.39

’a

0.34

'a

0.34

-a

0.28

TA

0.28

-o

0.27

da

0.26

sa

0.26

Activations Density 0.171%

language related to conflict and strong emotions

No Comments

No Known Activations