INDEX

Explanations

references to the Nobel Prize and related honors in scientific fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adier

-0.16

ahlen

-0.15

å·ŀ

-0.15

apat

-0.15

ä¸Ī

-0.14

ulas

-0.14

okol

-0.14

 danmark

-0.14

itect

-0.14

wipe

-0.14

POSITIVE LOGITS

ble

0.17

Responsive

0.15

ÙĬÙĨØ§Øª

0.15

 Welch

0.14

 Hutch

0.14

¬ģ

0.14

/MPL

0.14

allery

0.14

 Banks

0.14

Activations Density 0.003%

references to the Nobel Prize and related honors in scientific fields

No Comments

No Known Activations