INDEX

Explanations

phrases that indicate geographic areas and regional distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

rouw

-0.15

 å¤

-0.15

ÙĪÙĤÙģ

-0.13

chte

-0.13

 Karlov

-0.13

 forefront

-0.12

Î±Î½Î´

-0.12

 stride

-0.12

ONGO

-0.12

 Rencontre

-0.12

POSITIVE LOGITS

 location

0.48

 geography

0.48

 geographical

0.48

 geographic

0.45

 locations

0.45

 region

0.42

ge

0.42

location

0.39

 regions

0.38

-location

0.38

Activations Density 0.590%

phrases that indicate geographic areas and regional distinctions

No Comments

No Known Activations