INDEX

Explanations

references to rankings, leadership roles, and competitive contexts in sports and entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

stadt

-0.17

 Wenger

-0.16

eyer

-0.14

Ø¹Ø¯

-0.14

ngu

-0.14

OMEM

-0.14

_CLI

-0.14

.segment

-0.14

 segment

-0.13

 Liebe

-0.13

POSITIVE LOGITS

Gil

0.23

 import

0.21

 Rain

0.19

GINE

0.18

raq

0.18

 Alaska

0.18

 Imports

0.17

 Governors

0.17

 Import

0.17

 imports

0.17

Activations Density 0.001%

references to rankings, leadership roles, and competitive contexts in sports and entertainment

No Comments

No Known Activations