INDEX

Explanations

phrases that indicate location or geographic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Maher

-0.23

 Maid

-0.22

 Marty

-0.22

 milling

-0.22

 Maze

-0.21

 millis

-0.21

 Mills

-0.21

Mik

-0.20

 militia

-0.20

mik

-0.20

POSITIVE LOGITS

Mon

0.79

-mon

0.75

mon

0.75

Mon

0.75

mon

0.75

MON

0.73

_mon

0.69

MON

0.67

.mon

0.63

 ÐľÐ¾Ð½

0.62

Activations Density 0.180%

phrases that indicate location or geographic references

No Comments

No Known Activations