INDEX

Explanations

phrases indicating uncertainty or lack of clarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Selectable

-0.16

ppo

-0.14

not

-0.14

inos

-0.14

oci

-0.14

omer

-0.13

Ã¦re

-0.13

iore

-0.13

erek

-0.13

lat

-0.13

POSITIVE LOGITS

 whether

0.23

 precise

0.22

æĺ¯åĲ¦

0.21

 exact

0.21

 details

0.20

whether

0.20

 exactly

0.20

 precisely

0.19

 æĺ¯åĲ¦

0.18

exact

0.18

Activations Density 0.065%

phrases indicating uncertainty or lack of clarity

No Comments

No Known Activations