INDEX

Explanations

information related to recruitment processes and examination details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

bens

-0.18

 Canada

-0.17

Canada

-0.16

istrat

-0.15

trys

-0.15

ãĥ«ãĥī

-0.14

udd

-0.14

ÅĤ

-0.14

 Kaynak

-0.14

bish

-0.14

POSITIVE LOGITS

appa

0.18

 Pruitt

0.17

 Petty

0.17

opoulos

0.16

yar

0.16

 Lair

0.15

 Gallagher

0.15

oire

0.15

0.14

 TextAlign

0.14

Activations Density 0.250%

information related to recruitment processes and examination details

No Comments

No Known Activations