INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ouched

-0.15

jad

-0.13

imity

-0.13

pheric

-0.13

ropol

-0.13

htub

-0.13

entine

-0.13

 bÃ¡t

-0.13

atorium

-0.13

bis

-0.12

POSITIVE LOGITS

/Runtime

0.16

URLException

0.14

apgolly

0.14

Č

0.14

ì²Ļ

0.13

Äįel

0.13

.PropertyType

0.13

Ø±Ø§ÙĤ

0.13

 helicopt

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.