INDEX

Explanations

expressions of appreciation for someone's contributions and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

.tc

-0.18

kaar

-0.16

pard

-0.16

ulus

-0.14

itm

-0.14

abbo

-0.14

ander

-0.13

hei

-0.13

meric

-0.13

olume

-0.13

POSITIVE LOGITS

ä¸įçŁ¥

0.16

 leadership

0.15

_MULTI

0.14

PTH

0.13

 Contributions

0.13

 contributions

0.13

 qualities

0.13

ÐºÐ°Ð²

0.13

 Renaissance

0.13

Ø®Øµ

0.13

Activations Density 0.094%

expressions of appreciation for someone's contributions and achievements

No Comments

No Known Activations