INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

åħ¼

-0.16

 unlaw

-0.15

assed

-0.15

SEO

-0.14

 reass

-0.13

_Internal

-0.13

OTP

-0.13

patch

-0.13

 tits

-0.13

 Jenner

-0.13

POSITIVE LOGITS

 social

0.18

arti

0.16

ignon

0.15

HCI

0.15

 richer

0.15

Ã²i

0.14

 such

0.14

social

0.14

 user

0.14

oggles

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.