INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

sian

-0.16

awan

-0.15

å¯¸

-0.15

erb

-0.15

 forth

-0.14

kn

-0.14

scape

-0.14

aad

-0.14

à¸Ĺà¸°

-0.14

procs

-0.13

POSITIVE LOGITS

 organization

0.26

 organisation

0.25

able

0.24

organization

0.22

ably

0.21

/non

0.20

 organizations

0.20

ABLE

0.19

organisation

0.19

 organisations

0.18

Activations Density 0.009%

No Comments

No Known Activations