INDEX

Explanations

references to locations and regions in Canada

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Brow

-0.16

Ð²Ð¾Ð´

-0.15

 Theater

-0.15

nih

-0.15

 Resorts

-0.15

adoo

-0.15

eka

-0.15

 Verm

-0.15

Lik

-0.14

ihan

-0.13

POSITIVE LOGITS

isser

0.19

Canada

0.17

 Canada

0.17

ois

0.16

å²Ľ

0.16

erate

0.16

.ca

0.16

 Canadians

0.16

-wide

0.16

isson

0.16

Activations Density 0.086%

references to locations and regions in Canada

No Comments

No Known Activations