INDEX

Explanations

variations of the word "hail."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

elig

-0.16

zos

-0.15

cks

-0.15

plode

-0.15

sWith

-0.14

ampo

-0.14

cole

-0.14

adm

-0.14

arris

-0.14

zzarella

-0.14

POSITIVE LOGITS

0.17

rÃ³

0.16

Äĥng

0.16

igne

0.15

adi

0.15

·

0.15

 kond

0.14

rap

0.14

 Rapids

0.14

rana

0.14

Activations Density 0.012%

variations of the word "hail."

No Comments

No Known Activations