INDEX

Explanations

references to maps and mapping concepts

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

Maps

-0.19

Mappings

-0.18

iosa

-0.18

<HashMap

-0.17

_maps

-0.17

aries

-0.17

_MAPPING

-0.17

 mappings

-0.17

maps

-0.16

iesta

-0.16

POSITIVE LOGITS

illary

0.33

pping

0.29

reduce

0.28

maker

0.27

Reduce

0.26

ingu

0.25

quest

0.24

makers

0.24

SqlParameter

0.23

pper

0.23

Activations Density 0.031%

references to maps and mapping concepts

No Comments

No Known Activations