INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

‘

-0.18

-0.16

 [âĢ¦]

-0.16

ob

-0.15

vs

-0.14

 NSStringFromClass

-0.14

'(

-0.13

IP

-0.13

ovo

-0.13

eg

-0.13

POSITIVE LOGITS

radio

0.17

Radio

0.17

istrovstvÃŃ

0.17

adio

0.16

|RF

0.15

 listeners

0.15

 RADIO

0.15

 radio

0.15

 Radio

0.14

jom

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.