INDEX

Explanations

phrases that capture emotional intensity or personal reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ensch

-0.15

 Lens

-0.15

oe

-0.15

rello

-0.14

å¥ı

-0.14

Lens

-0.14

achel

-0.14

ument

-0.14

å½¹

-0.14

åħ±

-0.14

POSITIVE LOGITS

liÅ¡

0.15

/MPL

0.15

ungen

0.15

_TypeDef

0.15

/Internal

0.15

(éĩĳ

0.14

-NLS

0.14

NSK

0.14

 molec

0.14

.www

0.14

Activations Density 0.140%

phrases that capture emotional intensity or personal reflections

No Comments

No Known Activations