INDEX

Explanations

phrases indicating influence or significant impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

terra

-0.14

 Heap

-0.14

_blob

-0.14

åĥ

-0.14

isÃŃ

-0.13

CLUDED

-0.13

ertos

-0.13

Indexed

-0.13

 disposable

-0.13

_PCI

-0.13

POSITIVE LOGITS

 greater

0.32

 considerable

0.30

greater

0.30

 strong

0.27

 greatest

0.27

 immense

0.25

 substantial

0.23

 Greater

0.23

 extensive

0.23

Greater

0.22

Activations Density 0.210%

phrases indicating influence or significant impact

No Comments

No Known Activations