INDEX

Explanations

proper nouns and specific technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

alars

-0.15

uur

-0.15

 opendir

-0.14

ê²©

-0.14

pha

-0.14

eltas

-0.14

sher

-0.14

la

-0.14

lid

-0.14

kam

-0.13

POSITIVE LOGITS

 Availability

0.19

èŃľ

0.17

Availability

0.17

è°±

0.15

aiser

0.15

ÙħÛĮÙĦ

0.14

AGO

0.14

BU

0.14

inki

0.14

isser

0.14

Activations Density 0.039%

proper nouns and specific technical terms

No Comments

No Known Activations