INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

¶Į

-0.14

urai

-0.14

rink

-0.14

ull

-0.14

_UNDEF

-0.14

SystemService

-0.14

.Ultra

-0.14

ijken

-0.13

indre

-0.13

izards

-0.13

POSITIVE LOGITS

uet

0.17

ervas

0.15

asal

0.15

0.14

æ»ħ

0.14

Paz

0.14

 Hang

0.13

AGMA

0.13

 Chew

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.