INDEX

Explanations

terms associated with limitations and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

abant

-0.15

agina

-0.14

oky

-0.14

Ø¨Ø±ÛĮ

-0.14

quia

-0.14

 requ

-0.14

eyim

-0.13

 Geile

-0.13

tings

-0.13

abin

-0.13

POSITIVE LOGITS

ful

0.17

ulous

0.16

edly

0.15

Else

0.15

alth

0.14

pio

0.14

Ïİ

0.14

able

0.14

ÏĦÎŃ

0.14

ìłģìĿ¸

0.14

Activations Density 0.371%

terms associated with limitations and classifications

No Comments

No Known Activations