INDEX

Explanations

mentions of the word "lack" and its variations, indicating deficiencies or absences in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

borg

-0.18

gfx

-0.17

cem

-0.16

undle

-0.16

ÄĻk

-0.16

isci

-0.16

OLE

-0.15

ailer

-0.15

anca

-0.15

iants

-0.15

POSITIVE LOGITS

ada

0.40

lust

0.33

ey

0.28

adas

0.24

uster

0.23

0.22

ADA

0.22

nowledge

0.22

ade

0.21

idas

0.21

Activations Density 0.014%

mentions of the word "lack" and its variations, indicating deficiencies or absences in various contexts

No Comments

No Known Activations