INDEX

Explanations

phrases related to global influence and reputation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

åħ¨åĽ½

-0.19

 Nationwide

-0.16

ysqli

-0.15

 nationwide

-0.15

soever

-0.15

StateException

-0.15

 ìłĦêµŃ

-0.14

ingen

-0.14

rose

-0.14

 Universe

-0.14

POSITIVE LOGITS

/world

0.24

/global

0.23

ToLocal

0.21

/local

0.18

aux

0.16

(Global

0.15

reach

0.15

 scope

0.15

-reaching

0.15

 standards

0.15

Activations Density 0.100%

phrases related to global influence and reputation

No Comments

No Known Activations