INDEX

Explanations

references to specific geographical locations, particularly cities and states in India

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

edList

-0.14

 succes

-0.14

ablish

-0.14

abeth

-0.13

çľī

-0.13

bug

-0.13

aket

-0.13

 Ð½Ð°Ð¼

-0.13

.fi

-0.13

agna

-0.13

POSITIVE LOGITS

 Bris

0.16

ãĥ¼ãĥª

0.16

0.15

à¸į

0.15

0.14

à¹Īà¸Ńà¸Ļ

0.14

erd

0.14

 INSTANCE

0.14

idas

0.14

Activations Density 0.002%

references to specific geographical locations, particularly cities and states in India

No Comments

No Known Activations