INDEX

Explanations

titles or names associated with cinematic works or franchises, particularly involving superheroes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

↵

-0.17

ioned

-0.15

ordinate

-0.14

oll

-0.14

ILTER

-0.14

ain

-0.14

htar

-0.14

 franca

-0.14

POSITIVE LOGITS

 Eine

0.18

Volume

0.17

Ein

0.17

Unauthorized

0.17

 Reload

0.16

Authorized

0.16

 Volume

0.16

&e

0.15

An

0.15

Exposed

0.15

Activations Density 0.055%

titles or names associated with cinematic works or franchises, particularly involving superheroes

No Comments

No Known Activations