INDEX

Explanations

instances of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ython

-0.16

 bunch

-0.16

 brightest

-0.16

uÃŃ

-0.15

gon

-0.15

 happiest

-0.15

chwitz

-0.15

 widest

-0.15

ussen

-0.14

POSITIVE LOGITS

 opposite

0.24

 equivalent

0.22

 result

0.22

 envy

0.21

 perfect

0.21

ologically

0.20

 sort

0.19

 norm

0.19

 pits

0.18

 inverse

0.17

Activations Density 0.250%

instances of the word "the"

No Comments

No Known Activations