INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eken

-0.17

ilden

-0.14

atsu

-0.14

ddy

-0.13

rito

-0.13

hti

-0.13

ovÃ½

-0.13

dae

-0.13

abyte

-0.13

Ãªs

-0.13

POSITIVE LOGITS

Ø§ÙĨØ¯

0.14

shuffle

0.14

 Werner

0.14

ØŃÙĨ

0.14

awan

0.14

inh

0.13

cak

0.13

.shell

0.13

 redund

0.13

smr

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.