INDEX

Explanations

references to medical trials and immunological data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hamilton

-0.15

Stretch

-0.15

 Stretch

-0.15

 Cornell

-0.14

 Syracuse

-0.14

łí

-0.14

amet

-0.14

 thirsty

-0.14

/device

-0.14

 stretched

-0.13

POSITIVE LOGITS

Ig

0.29

 glob

0.25

oglob

0.23

 heavy

0.21

glob

0.21

 plasma

0.21

 Heavy

0.20

 Plasma

0.20

heavy

0.19

 gamm

0.19

Activations Density 0.018%

references to medical trials and immunological data

No Comments

No Known Activations