INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ruba

-0.15

gii

-0.15

ubs

-0.15

aken

-0.15

putc

-0.15

.baidu

-0.15

.lt

-0.15

.uc

-0.15

ivec

-0.14

UBY

-0.14

POSITIVE LOGITS

+xml

0.16

iani

0.16

ynes

0.15

áºŃu

0.15

Ã¨o

0.15

 Guaranteed

0.14

èĮĤ

0.14

iers

0.14

ÐµÑĢÐµÐ¶

0.14

vet

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.