INDEX

Explanations

articles and adjectives that characterize nouns, particularly in relation to notable entities or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

alion

-0.17

edian

-0.17

asl

-0.16

andex

-0.15

its

-0.14

ordes

-0.14

 nursing

-0.13

heed

-0.13

 Ipsum

-0.13

ucher

-0.12

POSITIVE LOGITS

imli

0.17

ReadWrite

0.14

SPELL

0.14

 Lesson

0.14

 EventHandler

0.14

LAY

0.13

LET

0.13

 Glover

0.13

 lesson

0.13

ifu

0.13

Activations Density 0.133%

articles and adjectives that characterize nouns, particularly in relation to notable entities or titles

No Comments

No Known Activations