INDEX

Explanations

specific types of data entities or biological classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Duty

-0.16

 Dare

-0.15

untas

-0.15

omo

-0.15

loid

-0.15

à¸´à¸ģà¸²à¸£

-0.14

 Readonly

-0.14

drag

-0.14

plat

-0.13

.assignment

-0.13

POSITIVE LOGITS

ERSIST

0.15

obil

0.15

yon

0.14

aurant

0.14

ngth

0.14

Æ°á»Łng

0.14

izard

0.13

raki

0.13

uf

0.13

ectl

0.13

Activations Density 0.088%

specific types of data entities or biological classifications

No Comments

No Known Activations