INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Rehabilitation

-0.16

Äħd

-0.15

rieg

-0.14

zac

-0.14

/autoload

-0.14

 rehabilitation

-0.14

clid

-0.13

åıĸãĤĬ

-0.13

áº»

-0.13

amera

-0.13

POSITIVE LOGITS

nen

0.18

 Sutton

0.17

istung

0.15

lation

0.15

iane

0.15

 Gaul

0.14

 Walls

0.14

ibili

0.14

åı

0.14

calar

0.14

Activations Density 0.134%

No Comments

No Known Activations