INDEX

Explanations

specific numerical data and identifiers related to events and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Trump

-0.22

Trump

-0.21

 Bernie

-0.19

 nucle

-0.18

 Donald

-0.18

 Brexit

-0.17

 Zika

-0.17

 Mosul

-0.16

 Sanders

-0.16

 Spicer

-0.16

POSITIVE LOGITS

.scalablytyped

0.20

ÑĤÐ°Ð±

0.16

rometer

0.16

 trá»¥

0.15

omics

0.15

å¹³æĪĲ

0.15

overy

0.15

æĲº

0.15

Î¯Îº

0.15

IRD

0.14

Activations Density 0.125%

specific numerical data and identifiers related to events and products

No Comments

No Known Activations