INDEX

Explanations

mentions of medications and their associated terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

iggers

-0.17

itat

-0.16

iggins

-0.15

PKG

-0.15

igers

-0.15

-0.14

Scoped

-0.14

 liá»ģn

-0.14

imizer

-0.14

POSITIVE LOGITS

avn

0.15

afil

0.14

à¥ĩà¤ª

0.14

ayan

0.14

Î³Î·

0.14

/rss

0.14

ä¾

0.13

æ´ĭ

0.13

 Expires

0.13

 ÐĲÐ½Ð´

0.13

Activations Density 0.007%

mentions of medications and their associated terms

No Comments

No Known Activations