INDEX

Explanations

terms related to packing and organization of items

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

 Bowen

-0.23

Attachments

-0.17

ajes

-0.17

stras

-0.17

 bows

-0.17

illas

-0.16

bow

-0.16

utzer

-0.16

 kayn

-0.15

uÃ§

-0.15

POSITIVE LOGITS

ÂŃs

0.16

éĸĢ

0.15

heimer

0.15

Jud

0.15

Obr

0.14

ache

0.14

ust

0.14

 Evaluation

0.14

 bloom

0.14

 restructuring

0.14

Activations Density 0.007%

terms related to packing and organization of items

No Comments

No Known Activations