INDEX

Explanations

phrases related to significant events or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 ÏĦÎ·

-0.14

optgroup

-0.13

-0.12

ekim

-0.12

iyim

-0.12

 Innoc

-0.12

à¸±à¸Ļà¹Ģà¸Ľ

-0.12

 ÏĥÏĦÎ·

-0.12

xmm

-0.12

ighbor

-0.12

POSITIVE LOGITS

an

0.99

an

0.49

aan

0.47

(an

0.40

.an

0.40

-an

0.36

An

0.36

'an

0.35

_an

0.35

—an

0.34

Activations Density 0.476%

phrases related to significant events or experiences

No Comments

No Known Activations