INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 tomorrow

-0.17

Å¡ak

-0.15

ANC

-0.15

Tomorrow

-0.15

 Tomorrow

-0.14

.fail

-0.14

ABLE

-0.14

 influencers

-0.13

iale

-0.13

ãĥĲãĤ¹

-0.12

POSITIVE LOGITS

afone

0.16

abant

0.15

erator

0.15

olid

0.15

ouri

0.14

 discussion

0.14

 logs

0.14

iqueta

0.14

wiki

0.14

åŃĺæ¡£

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.