INDEX

Explanations

references to documents, articles, or sources related to a variety of topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.17

and

-0.17

ands

-0.16

Alv

-0.16

asion

-0.15

illy

-0.15

 unit

-0.14

il

-0.14

 given

-0.14

unit

-0.14

POSITIVE LOGITS

ocuk

0.20

anel

0.16

Ð»Ð¸Ð½Ð¸

0.15

.nih

0.15

 ê²

0.15

åĶ¯

0.15

Ø§ÙĬØ±

0.14

kker

0.14

 Kendrick

0.14

ÅĻeh

0.14

Activations Density 0.069%

references to documents, articles, or sources related to a variety of topics

No Comments

No Known Activations