INDEX

Explanations

specific locations and their descriptions in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ð°Ð½ÐºÐ°

-0.17

/apis

-0.15

chez

-0.15

 seat

-0.14

zyst

-0.14

licit

-0.14

Greater

-0.14

ÙĦØ³ÙĦ

-0.13

Ã¡Å¾

-0.13

 airports

-0.13

POSITIVE LOGITS

 main

0.26

main

0.24

 Main

0.23

 MAIN

0.20

Main

0.19

_main

0.19

MAIN

0.19

-main

0.18

.main

0.17

.Main

0.17

Activations Density 0.121%

specific locations and their descriptions in a narrative

No Comments

No Known Activations