INDEX

Explanations

words related to destruction or damage, particularly involving tearing

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

Å¡t

-0.15

ÑıÐ³

-0.15

venir

-0.15

AGR

-0.15

giene

-0.15

Ø§ÙĦÙĩ

-0.15

/stat

-0.14

imap

-0.14

piel

-0.14

ground

-0.14

POSITIVE LOGITS

habi

0.15

ufe

0.15

æī£

0.14

bles

0.14

aucoup

0.14

éı¡

0.14

xffffff

0.14

able

0.14

ingly

0.13

Ã¼gen

0.13

Activations Density 0.019%

words related to destruction or damage, particularly involving tearing

No Comments

No Known Activations