INDEX

Explanations

words and phrases indicating opportunities and potential actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

evin

-0.15

ifar

-0.15

Ð»ÑĥÑĪ

-0.14

ëŁ¼

-0.14

ioni

-0.13

Î¯

-0.13

ISK

-0.13

reon

-0.13

urance

-0.13

 Zukunft

-0.13

POSITIVE LOGITS

 aprove

0.56

 exploit

0.52

 exploitation

0.50

 exploited

0.46

 capital

0.45

 capitalize

0.44

 exploiting

0.43

åĪ©çĶ¨

0.43

 exploits

0.43

explo

0.40

Activations Density 0.320%

words and phrases indicating opportunities and potential actions

No Comments

No Known Activations