INDEX

Explanations

mentions of interviews, particularly focusing on their frequency and context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ovit

-0.18

ÑĥÐ½Ðº

-0.16

otch

-0.15

heid

-0.15

ĺ

-0.14

vie

-0.14

ioc

-0.14

ilded

-0.14

ensus

-0.13

POSITIVE LOGITS

ees

0.29

ee

0.22

 conducted

0.19

ing

0.16

eea

0.15

ead

0.15

stakes

0.15

 Conduct

0.15

ables

0.15

ingen

0.15

Activations Density 0.014%

mentions of interviews, particularly focusing on their frequency and context

No Comments

No Known Activations