INDEX

Explanations

terms related to interaction and communication in online contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

oller

-0.16

 Leigh

-0.15

 inherited

-0.14

èĲ

-0.14

 Geile

-0.14

ìĶ

-0.13

ÑĢÐµÐ½Ð¸Ñı

-0.13

 Ange

-0.13

eric

-0.13

 Zucker

-0.13

POSITIVE LOGITS

 through

0.18

urdy

0.16

 Ð²Ð´

0.16

 æł

0.15

qv

0.15

 Mercer

0.14

 mast

0.14

 Through

0.14

ored

0.14

through

0.14

Activations Density 0.001%

terms related to interaction and communication in online contexts

No Comments

No Known Activations