INDEX

Explanations

numerical statistics and percentages related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 biÃ§imde

-0.22

Everybody

-0.21

 somebody

-0.21

 ÏĢÏīÏĤ

-0.20

 Somebody

-0.20

ologic

-0.19

Though

-0.18

ÙĶ

-0.17

instance

-0.17

 anybody

-0.17

POSITIVE LOGITS

0.22

Ùª

0.20

0.19

!--

0.19

Ì

0.19

0.18

 analyzes

0.18

ðŁ

0.16

ie

0.15

Hoy

0.15

Activations Density 0.827%

numerical statistics and percentages related to various subjects

No Comments

No Known Activations