INDEX

Explanations

terms related to innovative engineering and design principles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

avax

-0.16

.Dial

-0.15

avour

-0.15

tura

-0.15

ivor

-0.15

 Gamb

-0.15

_strategy

-0.14

_workers

-0.14

annel

-0.14

vester

-0.13

POSITIVE LOGITS

 conversion

0.22

conversion

0.22

 converted

0.21

 Conversion

0.20

convert

0.20

 convert

0.20

 conversions

0.19

 Converted

0.19

Conversion

0.19

 converts

0.19

Activations Density 0.001%

terms related to innovative engineering and design principles

No Comments

No Known Activations