INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÂŃi

-0.17

ãĤĵãģ¨

-0.16

ÎµÎ²

-0.15

RectTransform

-0.14

sic

-0.14

:UITableView

-0.14

.cls

-0.14

iphone

-0.13

ont

-0.13

.insertBefore

-0.13

POSITIVE LOGITS

0.22

,)

0.15

’

0.15

 anyway

0.14

old

0.14

---

0.14

or

0.14

 repar

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.