INDEX

Explanations

terms and phrases related to diseases and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

cene

-0.17

 Telescope

-0.16

.writeValue

-0.15

akov

-0.15

 Ghost

-0.14

esl

-0.14

 Panda

-0.14

 fragile

-0.14

 divert

-0.14

ubi

-0.14

POSITIVE LOGITS

 ticks

0.49

 tick

0.49

 Tick

0.43

tick

0.40

Tick

0.37

 Lyme

0.37

Ticks

0.34

.tick

0.33

 TICK

0.33

ticks

0.33

Activations Density 0.011%

terms and phrases related to diseases and medical conditions

No Comments

No Known Activations