INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 derp

-0.18

ÐµÑĢÑĤÐ°

-0.14

aily

-0.14

emaker

-0.14

intersection

-0.14

.Executor

-0.13

âłĢ

-0.13

 Commerce

-0.13

Https

-0.13

ÑĨÑĥ

-0.13

POSITIVE LOGITS

 forum

0.17

 postings

0.16

REAM

0.16

 Forum

0.16

 wakeup

0.15

Anonymous

0.15

 readers

0.15

/forum

0.14

Forum

0.14

 reve

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.