INDEX

Explanations

phrases indicating conditions or circumstances that vary based on context

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

ware

-0.16

imens

-0.15

utschen

-0.14

 Freeze

-0.14

chen

-0.14

rouw

-0.14

hesive

-0.14

pra

-0.14

zes

-0.14

uter

-0.13

POSITIVE LOGITS

 whether

0.17

TestFixture

0.15

ÐºÑĥÐ»

0.15

cela

0.15

 vintage

0.14

 degree

0.14

cdf

0.14

èľ

0.14

vil

0.14

 weather

0.14

Activations Density 0.038%

phrases indicating conditions or circumstances that vary based on context

No Comments

No Known Activations