INDEX

Explanations

instances of the word "have" and its variations indicating possession or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

umat

-0.15

oogle

-0.14

éĩı

-0.13

bins

-0.13

ë¶Ħ

-0.13

Erk

-0.13

acios

-0.13

offee

-0.13

udent

-0.13

retch

-0.13

POSITIVE LOGITS

 shown

0.24

 applications

0.23

 received

0.22

Applications

0.22

 recently

0.22

 Applications

0.22

 proven

0.20

applications

0.20

 lead

0.19

 lately

0.19

Activations Density 0.039%

instances of the word "have" and its variations indicating possession or existence

No Comments

No Known Activations