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

à¸£à¸°

-0.14

emer

-0.14

 inversion

-0.14

edition

-0.14

vic

-0.14

Ã©r

-0.13

 Tyson

-0.13

Transpose

-0.13

-piece

-0.13

chop

-0.13

POSITIVE LOGITS

 Cummings

0.18

 circ

0.16

prene

0.15

Cum

0.15

uilder

0.14

bout

0.14

pau

0.14

Cum

0.14

 Interr

0.14

isini

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.