INDEX

Explanations

mentions of prominent organizations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ãĥŃãĥ¼

-0.17

okit

-0.15

 nature

-0.15

 defaultManager

-0.15

kami

-0.15

vale

-0.15

nature

-0.15

ooter

-0.15

angen

-0.14

Ð¼Ð°Ð¼Ð¸

-0.14

POSITIVE LOGITS

ê·Ģ

0.17

-wide

0.16

Ã©k

0.16

inals

0.15

als

0.15

ÅĻeh

0.15

çĴ

0.14

zens

0.14

icals

0.14

inal

0.14

Activations Density 0.414%

mentions of prominent organizations and entities

No Comments

No Known Activations