INDEX

Explanations

occurrences 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

èµĦæł¼

-0.15

ilan

-0.15

advert

-0.14

éł

-0.14

 Horton

-0.14

stan

-0.14

VID

-0.13

Yar

-0.13

Ð¾ÑĢÐ°Ñı

-0.13

POSITIVE LOGITS

thon

0.15

we

0.15

unce

0.15

 Donovan

0.15

otte

0.15

oples

0.15

urement

0.14

erdem

0.14

ures

0.14

usercontent

0.14

Activations Density 0.103%

occurrences of the word "the"

No Comments

No Known Activations