INDEX

Explanations

phrases and actions related to transformative experiences and emotional expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

uite

-0.17

rente

-0.15

rame

-0.15

IGIN

-0.15

elpers

-0.15

vrd

-0.15

INVAL

-0.15

ober

-0.15

ÅĻeb

-0.15

quivo

-0.14

POSITIVE LOGITS

0.17

0.15

 totiÅ¾

0.15

 sooner

0.15

 nÃ¤

0.14

ifs

0.14

 namely

0.14

Roy

0.14

Activations Density 0.217%

phrases and actions related to transformative experiences and emotional expressions

No Comments

No Known Activations