INDEX

Explanations

references to academic accomplishments and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

/modules

-0.17

ÎºÎ¿ÏĤ

-0.15

umer

-0.15

 Mund

-0.15

_modules

-0.15

omat

-0.15

 matrimon

-0.14

 æ¯

-0.14

 Maiden

-0.14

.modules

-0.14

POSITIVE LOGITS

 Michael

1.23

MIC

1.10

Michael

1.09

 michael

1.05

 Miche

1.01

MIC

0.98

 Mike

0.96

mic

0.96

 Michaels

0.94

Mic

0.93

Activations Density 0.268%

references to academic accomplishments and awards

No Comments

No Known Activations