INDEX

Explanations

answers or solutions provided in a question-and-answer format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

vale

-0.15

lie

-0.14

lia

-0.14

 }};↵

-0.14

weeney

-0.14

ants

-0.13

hÃµes

-0.13

aviest

-0.13

inspace

-0.13

umps

-0.13

POSITIVE LOGITS

0.23

 Answer

0.18

:↵

0.17

:↵↵

0.17

Ans

0.17

 answering

0.17

 answered

0.16

 answer

0.15

Ans

0.15

answer

0.15

Activations Density 0.016%

answers or solutions provided in a question-and-answer format

No Comments

No Known Activations