INDEX

Explanations

references to recurring events or situations over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

atron

-0.17

reau

-0.17

orpion

-0.17

immel

-0.16

metatable

-0.16

kee

-0.15

ãĥ»ãĥ»

-0.14

gle

-0.14

horn

-0.14

Ä©

-0.14

POSITIVE LOGITS

 span

0.28

 rapid

0.24

 mere

0.21

 within

0.20

 spans

0.20

 Rapid

0.20

rapid

0.19

ä¸įåĪ°

0.18

Span

0.18

 Span

0.18

Activations Density 0.064%

references to recurring events or situations over time

No Comments

No Known Activations