INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

fully

-0.18

ically

-0.17

far

-0.17

rop

-0.16

pole

-0.16

mant

-0.15

phan

-0.15

reich

-0.15

Î¼ÎµÎ¹

-0.14

ildi

-0.14

POSITIVE LOGITS

xeb

0.17

utzer

0.16

utch

0.16

nown

0.16

masked

0.15

ometr

0.15

artz

0.15

ombs

0.15

ÐµÐ½ÑĤÐ¸

0.14

/Home

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.