INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

éĳĳ

-0.18

ears

-0.17

iges

-0.15

ieder

-0.15

.handleClick

-0.15

 ÙģÙĤØ¯

-0.15

ä»ģ

-0.15

RLF

-0.14

Ø±ÛĮÙħ

-0.14

é

-0.14

POSITIVE LOGITS

 individuals

0.17

co

0.16

 actors

0.16

 actor

0.15

 typically

0.15

 mobil

0.15

 internal

0.14

 outcomes

0.14

ist

0.14

 individual

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.