INDEX

Explanations

terminology related to medical conditions and pharmaceutical products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 endregion

-0.15

itch

-0.15

ÑĮÑİ

-0.15

abus

-0.15

åĪ»

-0.14

iker

-0.14

olog

-0.14

ITCH

-0.14

Cls

-0.14

 Digest

-0.14

POSITIVE LOGITS

0.19

overn

0.18

 online

0.18

online

0.17

 overnight

0.16

-online

0.16

onest

0.16

0.15

ifax

0.15

ouston

0.14

Activations Density 0.008%

terminology related to medical conditions and pharmaceutical products

No Comments

No Known Activations