INDEX

Explanations

phrases indicating inclusion or association with a group

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Î»ÎµÏį

-0.16

ISCO

-0.15

Ø±ÙģØ©

-0.15

ãģ»ãģ©

-0.15

 Pist

-0.14

 -----------------------------------------------------------------------------↵

-0.14

marks

-0.14

ety

-0.14

anca

-0.14

UFF

-0.14

POSITIVE LOGITS

 others

0.58

others

0.46

 Others

0.44

Others

0.40

 other

0.32

 otros

0.29

 anderen

0.27

 autres

0.27

 altri

0.25

 outros

0.24

Activations Density 0.009%

phrases indicating inclusion or association with a group

No Comments

No Known Activations