INDEX

Explanations

references to financial terms or transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

endar

-0.16

brush

-0.16

cin

-0.15

urette

-0.15

een

-0.15

rique

-0.15

ening

-0.15

urbation

-0.14

ulence

-0.14

athan

-0.14

POSITIVE LOGITS

ishing

0.26

icky

0.26

ISHED

0.25

anical

0.22

anc

0.22

ancial

0.22

stagram

0.21

ANC

0.20

anz

0.20

ned

0.20

Activations Density 0.012%

references to financial terms or transactions

No Comments

No Known Activations