INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Seal

-0.16

èĨ

-0.15

uco

-0.15

 halk

-0.14

chner

-0.13

Ð°Ð½ÑģÐ¸

-0.13

 Ð¾Ð³ÑĢÐ°

-0.13

 Yuan

-0.13

 perhaps

-0.13

aben

-0.13

POSITIVE LOGITS

 policym

0.19

 whose

0.16

whose

0.14

ogg

0.14

ipc

0.14

jab

0.14

omain

0.14

ypy

0.13

Î¸

0.13

pta

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.