INDEX

Explanations

references to changes in media or entertainment formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

.scalablytyped

-0.22

 jenter

-0.15

(æĹ¥

-0.15

rvÃ©

-0.15

 araya

-0.14

epar

-0.14

geben

-0.14

(çģ«

-0.14

ansson

-0.14

.Foundation

-0.14

POSITIVE LOGITS

 erst

0.18

Leh

0.18

 Soviet

0.16

 former

0.16

oner

0.16

 formerly

0.15

èĨ

0.15

Rue

0.15

Ð°ÑĩÐµ

0.15

unct

0.15

Activations Density 0.236%

references to changes in media or entertainment formats

No Comments

No Known Activations