INDEX

Explanations

entities and references to leadership and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ardown

-0.17

 will

-0.16

 ought

-0.15

Ð¸ÑĪ

-0.15

ozilla

-0.15

Ã©ment

-0.15

may

-0.15

 should

-0.15

nier

-0.15

 would

-0.15

POSITIVE LOGITS

be

0.29

 ever

0.20

 Ever

0.17

iden

0.15

-int

0.15

 happen

0.14

dens

0.14

ÏĮÎ½

0.14

ASIC

0.14

nt

0.14

Activations Density 0.069%

entities and references to leadership and governance

No Comments

No Known Activations