INDEX

Explanations

words related to revelation and significant insights or disclosures

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

eldorf

-0.18

usta

-0.16

osy

-0.15

uir

-0.15

à¸Ĺà¸²à¸Ļ

-0.15

elman

-0.15

arov

-0.14

Fir

-0.14

Mob

-0.14

vrd

-0.14

POSITIVE LOGITS

mts

0.17

 Worm

0.16

MT

0.15

ariat

0.15

ives

0.15

uxe

0.15

IRS

0.15

ĵ

0.15

ÑģÑĮ

0.14

enity

0.14

Activations Density 0.008%

words related to revelation and significant insights or disclosures

No Comments

No Known Activations