INDEX

Explanations

geographical references and names related to locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

adelphia

-0.15

cha

-0.15

 ç´

-0.14

olon

-0.14

éĤ¦

-0.14

.lu

-0.14

ÑģÐ¾Ð»

-0.14

-sama

-0.14

ixel

-0.14

ÙĪØ±ÙĨ

-0.14

POSITIVE LOGITS

 Saga

0.25

 Send

0.24

 Okay

0.23

 Pref

0.23

Eh

0.23

pref

0.23

Gun

0.22

 Koch

0.22

Pref

0.21

Ni

0.21

Activations Density 0.027%

geographical references and names related to locations

No Comments

No Known Activations