INDEX

Explanations

references to distances or measures involving "miles" and "milestones."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

elder

-0.18

all

-0.17

desk

-0.16

luck

-0.15

eldo

-0.15

like

-0.15

ampled

-0.14

nier

-0.14

byn

-0.14

warts

-0.14

POSITIVE LOGITS

stones

0.27

age

0.22

-long

0.21

stone

0.20

AGE

0.20

 Marker

0.19

-marker

0.19

 marker

0.19

-wide

0.18

umin

0.17

Activations Density 0.023%

references to distances or measures involving "miles" and "milestones."

No Comments

No Known Activations