INDEX

Explanations

terms related to medical conditions and procedures, particularly concerning tumors and brain surgery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

çŃĭ

-0.16

 Trib

-0.15

hape

-0.15

 skin

-0.15

çĭĲ

-0.15

eum

-0.15

 bron

-0.15

.skin

-0.15

skin

-0.15

jeta

-0.15

POSITIVE LOGITS

 Brain

0.30

 brain

0.29

 cere

0.28

Brains

0.27

 skull

0.27

èħ¦

0.26

Brain

0.26

 brains

0.25

brain

0.25

 Skull

0.25

Activations Density 0.035%

terms related to medical conditions and procedures, particularly concerning tumors and brain surgery

No Comments

No Known Activations