INDEX

Explanations

titles and roles associated with leadership and professional positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

abo

-0.17

 punch

-0.17

emmel

-0.15

edata

-0.15

-0.14

edReader

-0.14

 punches

-0.14

acher

-0.14

lut

-0.14

POSITIVE LOGITS

gc

0.16

rtl

0.16

(CharSequence

0.15

ldr

0.14

uner

0.14

lich

0.14

wc

0.14

lien

0.14

acomment

0.14

scriber

0.14

Activations Density 0.011%

titles and roles associated with leadership and professional positions

No Comments

No Known Activations