INDEX

Explanations

references to new products or trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

pole

-0.15

amaz

-0.15

ote

-0.14

ulong

-0.14

ogl

-0.14

/video

-0.13

/h

-0.13

phan

-0.13

asks

-0.13

ories

-0.13

POSITIVE LOGITS

swire

0.27

bies

0.22

-found

0.21

foundland

0.20

ish

0.20

/new

0.19

é²ľ

0.18

letters

0.18

sworth

0.18

-old

0.17

Activations Density 0.138%

references to new products or trends

No Comments

No Known Activations