INDEX

Explanations

phrases discussing governance and leadership issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ê±°ëŀĺê°Ģ

-0.15

adlo

-0.14

ÌĢ

-0.14

Ø¨ÙĪØ§Ø³Ø·Ø©

-0.14

LayoutConstraint

-0.14

ì£

-0.14

Prostit

-0.14

HAL

-0.14

ElementsBy

-0.13

_Osc

-0.13

POSITIVE LOGITS

 head

0.18

head

0.16

 president

0.15

Pon

0.15

 heads

0.15

VS

0.14

init

0.14

 TMPro

0.14

/head

0.14

 personally

0.14

Activations Density 0.524%

phrases discussing governance and leadership issues

No Comments

No Known Activations