INDEX

Explanations

references to employees and their engagement within an organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aben

-0.17

dsn

-0.16

berapa

-0.16

ettle

-0.16

woo

-0.15

Ã©ny

-0.14

zza

-0.14

UCH

-0.14

ighth

-0.14

duk

-0.14

POSITIVE LOGITS

 working

0.16

 manual

0.15

 work

0.15

 Shake

0.14

ington

0.14

 shake

0.14

pga

0.13

 vote

0.13

 route

0.13

Activations Density 0.343%

references to employees and their engagement within an organization

No Comments

No Known Activations