INDEX

Explanations

concepts related to identity and social issues

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Unless

-0.15

 Unless

-0.15

unless

-0.14

 unless

-0.14

.cum

-0.13

Yet

-0.13

Equivalent

-0.13

ãĢĤä½Ĩ

-0.12

çĶļèĩ³

-0.12

Ø§ÙħØ§

-0.12

POSITIVE LOGITS

 focusing

0.29

 examining

0.27

 using

0.26

 highlighting

0.26

vis

0.25

 examines

0.24

 versus

0.23

 examined

0.23

 drawing

0.23

 comparing

0.23

Activations Density 0.367%

concepts related to identity and social issues

No Comments

No Known Activations