INDEX

Explanations

phrases indicating importance or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

zd

-0.17

rets

-0.17

usercontent

-0.16

inki

-0.15

zers

-0.15

ENDOR

-0.15

ertoire

-0.15

OPSIS

-0.15

OLUMN

-0.14

.hwp

-0.14

POSITIVE LOGITS

acc

0.15

plier

0.15

airo

0.14

arda

0.14

rag

0.14

owi

0.14

null

0.14

acc

0.14

aller

0.13

æ¡Ĳ

0.13

Activations Density 0.076%

phrases indicating importance or significance

No Comments

No Known Activations