INDEX

Explanations

references to new developments or findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 currently

-0.26

 recent

-0.25

 presently

-0.23

currently

-0.22

 later

-0.20

å½ĵåīį

-0.20

 today

-0.19

 latest

-0.19

 earlier

-0.19

çĽ®åīį

-0.19

POSITIVE LOGITS

/current

0.30

;y

0.22

ral

0.21

inski

0.20

emente

0.20

elijk

0.19

mente

0.19

 addition

0.18

 additions

0.17

 Addition

0.17

Activations Density 0.045%

references to new developments or findings

No Comments

No Known Activations

references to new developments or findings

No Comments

No Known Activations