INDEX

Explanations

titles and roles related to executive positions within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

oard

-0.16

eneg

-0.15

ëĬ

-0.14

MOVED

-0.14

ÏĥÏĥÎ±

-0.14

gal

-0.14

atÃ¶r

-0.14

lington

-0.14

xis

-0.14

egg

-0.14

POSITIVE LOGITS

ship

0.21

0.15

ç¯Ģ

0.14

olest

0.14

osten

0.14

èĬĤ

0.14

ships

0.14

 neighb

0.14

ici

0.14

ento

0.14

Activations Density 0.006%

titles and roles related to executive positions within organizations

No Comments

No Known Activations