INDEX

Explanations

references to power dynamics and authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 à¹Ĩ

-0.15

ashtra

-0.15

ijke

-0.15

msgid

-0.15

èµ«

-0.14

abwe

-0.14

 selber

-0.14

itech

-0.14

anson

-0.14

elper

-0.14

POSITIVE LOGITS

0.15

 Voll

0.14

 denn

0.14

 dual

0.14

 Fritz

0.14

 appearances

0.13

/Page

0.13

sf

0.13

 appearance

0.13

sf

0.13

Activations Density 0.001%

references to power dynamics and authority

No Comments

No Known Activations