INDEX

Explanations

references to science and scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

iser

-0.18

itre

-0.17

tra

-0.17

neath

-0.17

ted

-0.16

rescia

-0.16

/down

-0.16

lander

-0.16

ting

-0.15

lass

-0.15

POSITIVE LOGITS

/engine

0.29

/math

0.27

-fiction

0.25

/Math

0.21

ENCES

0.19

/stat

0.18

 fiction

0.18

/art

0.18

emet

0.17

Activations Density 0.047%

references to science and scientific concepts

No Comments

No Known Activations