INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

enci

-0.19

Ð¾Ð²Ð°ÑĢÐ¸

-0.17

UserCode

-0.15

amac

-0.15

shortcode

-0.15

witter

-0.15

_Generic

-0.15

ToLeft

-0.14

 intptr

-0.14

eddar

-0.14

POSITIVE LOGITS

 Berm

0.16

 Bermuda

0.16

 actively

0.16

 Eston

0.15

 Estonia

0.15

 newsp

0.15

.lv

0.15

holm

0.14

 Balt

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.