INDEX

Explanations

titles and positions of authority figures

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

nte

-0.17

 Mezi

-0.15

tape

-0.15

ActivityIndicatorView

-0.15

ĴĮ

-0.14

 Dagger

-0.14

ÐµÑĤÑĥ

-0.14

'{@

-0.14

baugh

-0.14

etto

-0.13

POSITIVE LOGITS

0.15

asin

0.15

0.14

Vog

0.14

ynet

0.14

osl

0.14

ager

0.14

iks

0.14

ÙĪÙħØ§Øª

0.14

annes

0.13

Activations Density 0.098%

titles and positions of authority figures

No Comments

No Known Activations