INDEX

Explanations

references to the quantity "two."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ken

-0.15

insky

-0.15

vaz

-0.15

amines

-0.15

ÄĽnÃŃ

-0.14

 trespass

-0.14

gin

-0.14

ince

-0.14

åģı

-0.14

ChangeListener

-0.13

POSITIVE LOGITS

alom

0.16

riday

0.14

omon

0.14

Ã¨o

0.14

 Lost

0.14

ãĤĴãģ¤

0.13

.club

0.13

 Fell

0.13

hur

0.13

ì§Ī

0.13

Activations Density 0.107%

references to the quantity "two."

No Comments

No Known Activations