INDEX

Explanations

statements and claims about political or corporate actions and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.16

ÅĤem

-0.15

ãĥ«ãĥĪ

-0.14

ulu

-0.14

WO

-0.14

ColorBrush

-0.14

ìŀ¥ìĿĦ

-0.14

ÑĪÐ»Ð¾

-0.14

HEST

-0.14

æľŃ

-0.14

POSITIVE LOGITS

 himself

0.33

 company

0.31

his

0.29

 Company

0.25

 team

0.24

company

0.24

ãĥģãĥ¼ãĥł

0.24

åħ¬åı¸

0.23

his

0.23

 compan

0.20

Activations Density 0.431%

statements and claims about political or corporate actions and decisions

No Comments

No Known Activations