INDEX

Explanations

references to game development and associated teams

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

CLE

-0.15

eki

-0.15

 Patt

-0.14

rowned

-0.14

undry

-0.14

ellig

-0.14

ibilit

-0.13

ALER

-0.13

udu

-0.13

ritz

-0.13

POSITIVE LOGITS

ares

0.17

Rap

0.15

ource

0.15

 ç¥

0.14

rap

0.14

 Ø£Øµ

0.14

 licensee

0.13

ode

0.13

LOUR

0.13

 Lesser

0.13

Activations Density 0.075%

references to game development and associated teams

No Comments

No Known Activations