INDEX

Explanations

words and phrases related to medical terms and conditions

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

eh

-0.20

ehir

-0.19

ohn

-0.19

amente

-0.17

ech

-0.17

eam

-0.17

isin

-0.16

eff

-0.16

eeee

-0.16

rosse

-0.16

POSITIVE LOGITS

soever

0.27

rd

0.26

ilde

0.20

IGHL

0.20

ERSHEY

0.19

IGHLIGHT

0.18

ry

0.17

irst

0.17

TEGER

0.17

%%%%%%%%%%%%%%%%

0.17

Activations Density 2.393%

words and phrases related to medical terms and conditions

No Comments

No Known Activations