INDEX

Explanations

references to file paths and directories in coding or programming contexts

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

OfFile

-0.17

.twig

-0.16

å¨ĺ

-0.15

ahn

-0.14

.setView

-0.14

incinn

-0.14

alem

-0.14

Ú©ÙĪ

-0.14

Î¯Ïĥ

-0.13

 Haram

-0.13

POSITIVE LOGITS

 folder

0.23

 directory

0.20

 Folder

0.19

 folders

0.18

 íı´

0.18

 subdir

0.17

çĽ®å½ķ

0.16

_folder

0.15

ossier

0.15

-directory

0.15

Activations Density 0.092%

references to file paths and directories in coding or programming contexts

No Comments

No Known Activations