INDEX

Explanations

numerical data and references to support claims or arguments

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

-0.17

_inches

-0.14

errer

-0.14

 canh

-0.14

enerative

-0.14

à¸§à¸Ļ

-0.13

.MouseAdapter

-0.13

alic

-0.13

reds

-0.13

asive

-0.13

POSITIVE LOGITS

 according

0.27

 According

0.27

 Regarding

0.20

 underlying

0.20

according

0.20

 concerning

0.20

 Comple

0.20

 Depending

0.20

 regarding

0.19

 depending

0.19

Activations Density 0.016%

numerical data and references to support claims or arguments

No Comments

No Known Activations