INDEX

Explanations

phrases related to completing or filling out forms and documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

eff

-0.17

hg

-0.16

trak

-0.15

yles

-0.15

ziel

-0.15

.amazonaws

-0.14

em

-0.14

eme

-0.14

ease

-0.14

POSITIVE LOGITS

fill

0.31

filled

0.30

(fill

0.29

-fill

0.28

.Fill

0.28

Fill

0.27

 fill

0.27

 Fill

0.26

fills

0.26

fillable

0.25

Activations Density 0.027%

phrases related to completing or filling out forms and documents

No Comments

No Known Activations