INDEX

Explanations

past participles of verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

-0.22

asted

-0.17

lek

-0.16

ieÅ¼

-0.16

-0.15

marvin

-0.15

adows

-0.15

incident

-0.15

ologne

-0.15

olvers

-0.15

POSITIVE LOGITS

dy

0.26

gy

0.25

ifice

0.24

icts

0.22

0.21

die

0.21

ema

0.21

ging

0.21

uction

0.20

dress

0.20

Activations Density 0.007%

past participles of verbs

No Comments

No Known Activations