INDEX

Explanations

medical and biological terminology related to immune responses and disorders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

asket

-0.14

ãĥ¥ãĥ¼

-0.13

.cx

-0.13

ä¹±

-0.13

esterday

-0.13

rof

-0.13

arm

-0.13

olute

-0.13

oup

-0.13

CAF

-0.13

POSITIVE LOGITS

izza

0.18

isci

0.15

 Leban

0.14

GREE

0.14

 Suche

0.14

enderror

0.14

enario

0.13

iza

0.13

/Index

0.13

ddb

0.13

Activations Density 0.151%

medical and biological terminology related to immune responses and disorders

No Comments

No Known Activations