INDEX

Explanations

keywords related to significance and dependency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rows

-0.18

-Mar

-0.16

ÙĪØ§ÙĨ

-0.15

Ö

-0.14

bou

-0.14

olding

-0.14

dro

-0.14

arb

-0.14

åļ

-0.14

 underst

-0.14

POSITIVE LOGITS

zej

0.16

ãĥ«ãĤ¯

0.15

icted

0.15

etten

0.15

iÄĩ

0.15

ycastle

0.14

gether

0.14

oyal

0.14

ickest

0.14

åħ·

0.14

Activations Density 0.104%

keywords related to significance and dependency

No Comments

No Known Activations