INDEX

Explanations

terms related to technology products, specifically smartphones and gaming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

quential

-0.14

ofire

-0.14

ONGL

-0.13

ÐµÐ»Ðµ

-0.13

Ð°ÑĪ

-0.13

-quote

-0.12

otify

-0.12

resents

-0.12

FRING

-0.12

 defaultMessage

-0.12

POSITIVE LOGITS

 arriving

0.25

 delayed

0.23

 Coming

0.23

Arr

0.23

 confirmed

0.22

 Leak

0.22

Ann

0.22

 lands

0.22

 coming

0.22

 spotted

0.21

Activations Density 0.068%

terms related to technology products, specifically smartphones and gaming

No Comments

No Known Activations