INDEX

Explanations

phrases indicating the inclusion or availability of features and attributes in products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

SON

-0.14

chner

-0.14

aur

-0.14

 himself

-0.14

yle

-0.14

son

-0.14

itz

-0.14

 onResponse

-0.14

UNCH

-0.13

CoreApplication

-0.13

POSITIVE LOGITS

ITA

0.15

\↵

0.15

ì§ĳ

0.14

 split

0.14

isz

0.14

umbnails

0.14

 thÃ¹

0.14

 erotico

0.13

 âĹĦ

0.13

 Split

0.13

Activations Density 0.031%

phrases indicating the inclusion or availability of features and attributes in products or services

No Comments

No Known Activations