INDEX

Explanations

terms related to medical conditions and diagnostic criteria

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 zastup

-0.14

ä»Ģ

-0.14

lat

-0.14

ilver

-0.14

 Vall

-0.14

 lanc

-0.14

beros

-0.13

 Prim

-0.13

JECT

-0.13

POSITIVE LOGITS

ycz

0.18

ewis

0.17

fy

0.17

zyst

0.16

atoi

0.15

aniu

0.15

 normal

0.14

Ð»Ð¸Ð½Ð¸

0.14

anager

0.14

ownt

0.14

Activations Density 0.043%

terms related to medical conditions and diagnostic criteria

No Comments

No Known Activations