INDEX

Explanations

references to professional roles and associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

hole

-0.16

Vox

-0.15

ÐµÑĢÐ¾

-0.15

boarding

-0.15

ry

-0.15

ARE

-0.14

arrow

-0.14

joy

-0.14

tures

-0.14

POSITIVE LOGITS

-grade

0.28

ized

0.27

ization

0.23

ism

0.23

ised

0.22

izing

0.22

izes

0.21

ising

0.20

ize

0.20

isation

0.19

Activations Density 0.031%

references to professional roles and associations

No Comments

No Known Activations