INDEX

Explanations

prompts encouraging critical thinking and reflection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

arness

-0.15

usercontent

-0.14

 Hacker

-0.14

ãĥ¡ãĥ©

-0.14

æĤł

-0.14

.azure

-0.14

ecycle

-0.14

ucker

-0.13

ibaba

-0.13

aran

-0.13

POSITIVE LOGITS

 yourself

0.17

tout

0.16

åĲ§

0.16

ance

0.15

ables

0.15

0.14

 Yourself

0.14

ZA

0.14

able

0.14

Activations Density 0.067%

prompts encouraging critical thinking and reflection

No Comments

No Known Activations