INDEX

Explanations

references to scholarly work and opinions on various subjects, particularly regarding economics, history, and social commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Usage

-0.16

icolor

-0.15

arga

-0.15

 Guar

-0.15

aga

-0.14

 originally

-0.14

aversal

-0.14

æľĭ

-0.14

ropol

-0.13

MOT

-0.13

POSITIVE LOGITS

omik

0.17

AllWindows

0.14

_epi

0.14

/tos

0.14

repid

0.14

ContentLoaded

0.14

lendi

0.13

 OnTrigger

0.13

ResultsController

0.13

 Latter

0.13

Activations Density 0.153%

references to scholarly work and opinions on various subjects, particularly regarding economics, history, and social commentary

No Comments

No Known Activations