INDEX

Explanations

instances of the word "discover" and its variations, indicating a focus on exploration or revelation

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

unn

-0.19

uracy

-0.17

punkt

-0.16

ilia

-0.16

igi

-0.16

elsey

-0.16

soever

-0.15

rott

-0.15

ted

-0.14

hee

-0.14

POSITIVE LOGITS

ry

0.21

ries

0.18

ogue

0.17

rys

0.17

etten

0.16

ies

0.16

 ways

0.16

eres

0.15

ability

0.15

verse

0.15

Activations Density 0.025%

instances of the word "discover" and its variations, indicating a focus on exploration or revelation

No Comments

No Known Activations