INDEX

Explanations

instances of conflict or tension involving 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 both

-0.17

 BOTH

-0.16

missive

-0.15

 bÃ¥de

-0.15

 Both

-0.15

nock

-0.15

ãĤĵãģ¨

-0.14

both

-0.14

UpDown

-0.14

©

-0.14

POSITIVE LOGITS

 healed

0.18

 forever

0.17

 dynamics

0.16

 decades

0.16

 Scenario

0.15

 centuries

0.15

 shifted

0.15

 asla

0.15

dyn

0.15

 Critics

0.14

Activations Density 0.068%

instances of conflict or tension involving authority figures

No Comments

No Known Activations