INDEX

Explanations

references to historical individuals and their political impact

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

Nano

-0.18

 Nano

-0.17

 favor

-0.16

favor

-0.16

GIN

-0.16

 Global

-0.15

Hub

-0.15

Hub

-0.15

 favored

-0.15

 modeling

-0.14

POSITIVE LOGITS

0.26

0.21

ï¼ĪæĺŃåĴĮ

0.21

 USSR

0.21

 Thatcher

0.21

 Decimal

0.18

 Soviet

0.18

ICI

0.18

0.17

Activations Density 0.143%

references to historical individuals and their political impact

No Comments

No Known Activations