INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ulle

-0.17

hiba

-0.17

urette

-0.16

ulkan

-0.16

ulumi

-0.16

Ð±Ð¾Ð»

-0.15

Ø§Ø´

-0.14

brook

-0.14

oes

-0.13

ULA

-0.13

POSITIVE LOGITS

ourd

0.15

ingo

0.15

utz

0.15

 mini

0.14

 hedge

0.14

stal

0.14

ReturnType

0.14

hz

0.14

ppe

0.14

¦

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.