INDEX

Explanations

medical terms related to cancer and other diseases

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

iland

-0.18

rÃ¡l

-0.16

uyla

-0.15

INET

-0.15

ç«ĭãģ¦

-0.15

UpDown

-0.15

_Native

-0.15

ignKey

-0.15

Wik

-0.14

opolitan

-0.14

POSITIVE LOGITS

itis

0.18

 periodic

0.16

ahlen

0.16

ans

0.15

/tos

0.15

 fist

0.15

storm

0.15

 candid

0.15

ization

0.14

 spots

0.14

Activations Density 0.079%

medical terms related to cancer and other diseases

No Comments

No Known Activations