INDEX

Explanations

phrases expressing feelings of privilege and honor

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

lagen

-0.15

jud

-0.14

ily

-0.14

smouth

-0.14

.ag

-0.14

ook

-0.14

 æĺŁ

-0.13

ohl

-0.13

Thunk

-0.13

inn

-0.13

POSITIVE LOGITS

 privilege

0.62

 privileged

0.48

priv

0.43

 Priv

0.42

 prive

0.42

 priv

0.41

 privileges

0.41

privileged

0.40

Priv

0.38

 privile

0.36

Activations Density 0.133%

phrases expressing feelings of privilege and honor

No Comments

No Known Activations