INDEX

Explanations

references to color and shading, particularly in relation to shades of gray

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lah

-0.15

emmel

-0.15

tains

-0.15

onomy

-0.14

scape

-0.14

 misunder

-0.14

ansa

-0.14

.Management

-0.14

zers

-0.14

itis

-0.13

POSITIVE LOGITS

 Bakan

0.15

ãĥ¼ãĥ³

0.15

 competitive

0.14

vir

0.14

ãĢħ

0.14

ÅĦ

0.14

craft

0.14

oux

0.14

ula

0.13

Activations Density 0.012%

references to color and shading, particularly in relation to shades of gray

No Comments

No Known Activations