INDEX

Explanations

affirmations and agreements in conversation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

erras

-0.15

 dend

-0.14

à¤¸à¤°

-0.14

emachine

-0.14

repo

-0.14

essel

-0.14

rix

-0.14

 intended

-0.14

sk

-0.13

umba

-0.13

POSITIVE LOGITS

 Hlav

0.16

 indeed

0.15

ewe

0.14

 Bowman

0.14

agh

0.14

ManagerInterface

0.14

0.13

&&(

0.13

inde

0.13

Activations Density 0.311%

affirmations and agreements in conversation

No Comments

No Known Activations