INDEX

Explanations

phrases related to protests and public dissent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

OA

-0.15

IMER

-0.15

ause

-0.15

.compat

-0.14

OLE

-0.14

 Ð¾Ð±Ð¾ÑĢ

-0.14

 overcoming

-0.14

sounds

-0.14

ëłĪìĿ´

-0.14

.examples

-0.14

POSITIVE LOGITS

 perceived

0.32

 alleged

0.20

 allegedly

0.20

 lack

0.19

 perceive

0.17

 handling

0.17

 perce

0.17

lack

0.16

 treatment

0.16

abbit

0.15

Activations Density 0.235%

phrases related to protests and public dissent

No Comments

No Known Activations