INDEX

Explanations

references to cards and card-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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ilt

-0.19

OUS

-0.17

erties

-0.17

ilter

-0.16

ously

-0.16

inÃ§

-0.15

icz

-0.15

ous

-0.15

coming

-0.15

semester

-0.15

POSITIVE LOGITS

inality

0.28

holder

0.27

holders

0.27

inals

0.24

igan

0.23

inal

0.21

INAL

0.21

inally

0.20

iology

0.19

istry

0.18

Activations Density 0.022%

references to cards and card-related concepts

No Comments

No Known Activations