INDEX

Explanations

adjectives or phrases indicating comparison or contrast between options or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Olymp

-0.15

adi

-0.14

ikan

-0.14

qua

-0.14

inters

-0.14

ovo

-0.14

 minus

-0.14

IOC

-0.14

oven

-0.13

.imag

-0.13

POSITIVE LOGITS

ContentAlignment

0.17

.scalablytyped

0.16

 Lauderdale

0.16

/Dk

0.15

zon

0.15

rowsable

0.14

cion

0.14

 Truy

0.14

ospace

0.14

Bul

0.14

Activations Density 0.289%

adjectives or phrases indicating comparison or contrast between options or situations

No Comments

No Known Activations