INDEX

Explanations

references to locations, specifically Washington and related geographical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Tennessee

-0.18

 Bermuda

-0.17

 Illinois

-0.17

 Pennsylvania

-0.15

 Florida

-0.15

oc

-0.15

 Connecticut

-0.14

 Texas

-0.14

 Alabama

-0.14

POSITIVE LOGITS

 Seattle

0.64

Seattle

0.58

 Tacoma

0.57

 Spokane

0.50

Pu

0.45

 Seahawks

0.45

 Vancouver

0.44

WA

0.39

okane

0.38

Yak

0.37

Activations Density 0.240%

references to locations, specifically Washington and related geographical contexts

No Comments

No Known Activations