INDEX

Explanations

references to geographic locations and environmental impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

HW

-0.15

ubi

-0.15

 Locations

-0.15

Äĩe

-0.14

adesh

-0.14

âĶĲ

-0.13

uib

-0.13

.locations

-0.13

Locations

-0.13

 Coch

-0.13

POSITIVE LOGITS

 surrounding

0.85

 nearby

0.67

 Surround

0.60

 surround

0.57

 surrounds

0.57

 neighboring

0.54

 surroundings

0.54

 neighbouring

0.50

 adjacent

0.49

éĻĦè¿ĳ

0.49

Activations Density 0.320%

references to geographic locations and environmental impacts

No Comments

No Known Activations