INDEX

Explanations

abbreviations or shorthand notations related to medical conditions or treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

hb

-0.27

bh

-0.26

bÃ¡ch

-0.26

abh

-0.25

akh

-0.24

kh

-0.24

ikh

-0.24

abeth

-0.24

nh

-0.24

hek

-0.23

POSITIVE LOGITS

oe

0.14

ĮĢ

0.14

sa

0.14

sa

0.13

ae

0.13

aos

0.13

ra

0.13

eas

0.13

 raid

0.13

.eof

0.12

Activations Density 0.193%

abbreviations or shorthand notations related to medical conditions or treatments

No Comments

No Known Activations