INDEX

Explanations

references to specific locations and attractions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.Azure

-0.17

 Catalonia

-0.16

.Ptr

-0.16

hoo

-0.15

 coast

-0.15

 Tampa

-0.15

 Orioles

-0.15

.azure

-0.15

enek

-0.15

orca

-0.14

POSITIVE LOGITS

 Wyoming

0.43

Wy

0.27

wy

0.22

 Idaho

0.21

 Yellowstone

0.19

wy

0.19

Uint

0.17

 thyroid

0.17

Wy

0.17

 Uint

0.17

Activations Density 0.054%

references to specific locations and attractions

No Comments

No Known Activations