INDEX

Explanations

phrases indicating familiarity and knowledge about someone or something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

igo

-0.17

jure

-0.15

keley

-0.15

Ð½Ð°ÑĩÐµ

-0.14

jte

-0.14

ega

-0.14

&W

-0.14

ickey

-0.14

laps

-0.14

iew

-0.13

POSITIVE LOGITS

 grips

0.27

Gri

0.20

asty

0.19

 know

0.18

bottom

0.17

PointXYZ

0.16

Bottom

0.16

BOTTOM

0.15

 work

0.15

Activations Density 0.035%

phrases indicating familiarity and knowledge about someone or something

No Comments

No Known Activations