INDEX

Explanations

references to specific names or terms associated with places or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.21

eyes

-0.18

er

-0.18

uin

-0.18

ing

-0.18

ãĥ³ãĤ°

-0.18

-0.17

tÃ¼

-0.16

enko

-0.16

ega

-0.16

POSITIVE LOGITS

kers

0.25

sa

0.23

nowledge

0.23

ht

0.22

ker

0.22

uten

0.21

à¥įà¤·

0.21

ses

0.21

ladatel

0.20

hl

0.20

Activations Density 0.026%

references to specific names or terms associated with places or individuals

No Comments

No Known Activations