INDEX

Explanations

actions and verbs related to effort, assistance, and improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

to

-0.24

ë¥¼

-0.17

atts

-0.16

 Äĳá»ĥ

-0.16

/is

-0.15

-0.14

/UI

-0.14

hz

-0.14

ly

-0.14

 ÎµÏĢÎ¯ÏĥÎ·ÏĤ

-0.14

POSITIVE LOGITS

/remove

0.16

indre

0.16

/update

0.16

/save

0.15

jer

0.15

igate

0.15

ify

0.15

ieren

0.15

linky

0.15

ä¸Ģä¸ĭ

0.15

Activations Density 1.407%

actions and verbs related to effort, assistance, and improvement

No Comments

No Known Activations