INDEX

Explanations

references to locations and geographical entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

arakter

-0.16

obec

-0.15

ÌĢ

-0.14

FromNib

-0.14

ptron

-0.14

celik

-0.14

Next

-0.14

zig

-0.14

Ð¾ÑĩÐºÑĥ

-0.14

BuilderInterface

-0.13

POSITIVE LOGITS

 standpoint

0.29

 perspective

0.26

 perspectives

0.21

 sources

0.20

 Perspective

0.19

 inception

0.19

 lips

0.18

 Perspectives

0.18

ESC

0.18

pers

0.17

Activations Density 0.449%

references to locations and geographical entities

No Comments

No Known Activations