INDEX

Explanations

terms related to notification and communication

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

èīº

-0.15

 fossil

-0.14

Ø²Ø§Ø±

-0.14

å¥ī

-0.13

ourke

-0.13

vig

-0.13

coal

-0.13

äº¿

-0.13

ardi

-0.13

POSITIVE LOGITS

çĲ

0.16

elm

0.15

nge

0.14

ReadWrite

0.14

 kurs

0.14

ights

0.14

 Mast

0.14

 Func

0.14

ÑĢÑĥÑĩ

0.14

Ze

0.14

Activations Density 0.016%

terms related to notification and communication

No Comments

No Known Activations