INDEX

Explanations

references to "Box" and its associated numbers or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ustrial

-0.16

izr

-0.16

urre

-0.15

ufs

-0.15

odate

-0.15

reich

-0.15

ufen

-0.15

Dew

-0.15

udes

-0.14

Mug

-0.14

POSITIVE LOGITS

<dyn

0.25

(es

0.22

-sizing

0.22

(Box

0.21

.Box

0.21

.box

0.21

IsEmpty

0.20

-shadow

0.19

meer

0.18

(box

0.18

Activations Density 0.036%

references to "Box" and its associated numbers or categories

No Comments

No Known Activations