INDEX

Explanations

references to vehicles and automotive products

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

atomic

-0.15

apol

-0.15

-0.14

-flight

-0.14

 Titanic

-0.14

Raz

-0.14

 MÃ¶

-0.14

flight

-0.14

-0.13

POSITIVE LOGITS

 truck

0.20

mud

0.19

 rugged

0.18

 rough

0.18

 trucks

0.18

truck

0.18

 Truck

0.17

 muddy

0.17

Mud

0.17

 Trail

0.16

Activations Density 0.066%

references to vehicles and automotive products

No Comments

No Known Activations