INDEX

Explanations

references to the term "Plastics" or related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

yonel

-0.19

-0.18

ored

-0.16

obus

-0.16

an

-0.16

-0.15

olicit

-0.15

 plain

-0.15

anja

-0.15

implify

-0.15

POSITIVE LOGITS

ummer

0.23

atts

0.22

ural

0.21

zens

0.20

inth

0.20

enary

0.20

asm

0.20

umb

0.19

zen

0.19

ottage

0.19

Activations Density 0.012%

references to the term "Plastics" or related concepts

No Comments

No Known Activations