INDEX

Explanations

medical terminology related to brain conditions and diagnostic procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÑģÑİ

-0.17

Indented

-0.15

 âĹĦ

-0.15

 ?><?

-0.15

uros

-0.14

Typed

-0.14

ottes

-0.14

ancode

-0.14

ott

-0.13

ulk

-0.13

POSITIVE LOGITS

meli

0.15

 Crit

0.15

ras

0.14

ne

0.14

CG

0.14

ries

0.14

bee

0.14

CG

0.14

 util

0.14

Activations Density 0.054%

medical terminology related to brain conditions and diagnostic procedures

No Comments

No Known Activations