INDEX

Explanations

terms related to direction and directorial roles or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Directory

-0.19

directories

-0.18

directory

-0.18

 diret

-0.17

Directories

-0.17

-directory

-0.17

 directories

-0.17

DIRECT

-0.17

 directed

-0.17

çĽ®å½ķ

-0.17

POSITIVE LOGITS

ship

0.31

ivity

0.31

ial

0.30

ships

0.27

ate

0.27

ially

0.25

ality

0.25

orial

0.24

orate

0.22

ates

0.22

Activations Density 0.095%

terms related to direction and directorial roles or actions

No Comments

No Known Activations