INDEX

Explanations

references to Indian culture or entities

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

eden

-0.18

ãĤ·ãĤ§

-0.15

erdem

-0.15

ugins

-0.15

 McCart

-0.14

.ribbon

-0.14

moz

-0.14

æµª

-0.14

ushi

-0.14

 marshaller

-0.14

POSITIVE LOGITS

Mat

0.20

 game

0.20

Mat

0.19

 King

0.19

 king

0.18

 satin

0.18

Sat

0.18

 played

0.18

mat

0.18

sat

0.17

Activations Density 0.001%

references to Indian culture or entities

No Comments

No Known Activations