INDEX

Explanations

references to geographic locations and events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Chennai

-0.19

 Bahrain

-0.18

 Covent

-0.18

 Tamil

-0.18

ÑĢÐ°Ð±

-0.18

 tamil

-0.16

Singapore

-0.16

 Nass

-0.16

 Newark

-0.16

ilmington

-0.16

POSITIVE LOGITS

 Montana

0.66

 Yellowstone

0.46

 Helena

0.43

MT

0.42

Mont

0.40

 Glacier

0.37

 mont

0.35

 Mont

0.35

 Miss

0.35

MT

0.31

Activations Density 0.027%

references to geographic locations and events

No Known Activations