INDEX

Explanations

positive descriptors, particularly focusing on the word "a."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

hic

-0.16

agini

-0.15

anse

-0.15

ollect

-0.14

 Confidence

-0.14

agr

-0.13

gest

-0.13

 confidence

-0.13

range

-0.13

POSITIVE LOGITS

eyse

0.15

ê³Ħ

0.14

è¦

0.14

icari

0.14

Ø§ÙĨÙĬØ©

0.14

Ð»Ð¸ÑĪÐºÐ¾Ð¼

0.14

Ã©al

0.13

ModelProperty

0.13

Ð°ÑĢÐ°Ð¼

0.13

@s

0.13

Activations Density 0.154%

positive descriptors, particularly focusing on the word "a."

No Comments

No Known Activations