INDEX

Explanations

instances of the word "got" in various contexts

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

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

odic

-0.16

-0.15

ctr

-0.14

ertos

-0.14

istrat

-0.14

aire

-0.14

indsight

-0.14

oon

-0.13

inished

-0.13

hoo

-0.13

POSITIVE LOGITS

chas

0.33

cha

0.30

terdam

0.27

rid

0.22

CHA

0.22

chu

0.20

sta

0.19

ton

0.18

Ta

0.18

iate

0.18

Activations Density 0.022%

instances of the word "got" in various contexts

No Comments

No Known Activations