INDEX

Explanations

information about individuals' professional roles and backgrounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 sponsoring

-0.15

iffe

-0.15

-0.14

 Alone

-0.14

 sponsorship

-0.14

ÑģÐ¸ÑĤ

-0.14

 Phen

-0.14

[]{↵

-0.14

 Rounds

-0.14

[]

-0.13

POSITIVE LOGITS

 covering

0.23

 writing

0.20

 Reporting

0.19

covers

0.19

åĨĻ

0.19

 reporting

0.18

 covers

0.18

covering

0.18

 coverage

0.18

æĬ¥éģĵ

0.18

Activations Density 0.116%

information about individuals' professional roles and backgrounds

No Comments

No Known Activations