INDEX

Explanations

terms related to medical procedures and technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

/team

-0.17

riad

-0.17

patch

-0.17

Å¡t

-0.16

ipo

-0.16

 tense

-0.16

 tijd

-0.16

ime

-0.16

ext

-0.15

 timely

-0.15

POSITIVE LOGITS

ÑĩÐ°Ñģ

0.22

entieth

0.21

othy

0.19

itionally

0.19

 nhiÃªn

0.19

ãģĬãĤĬ

0.18

=T

0.18

quila

0.18

setter

0.17

esseract

0.17

Activations Density 2.031%

terms related to medical procedures and technical specifications

No Comments

No Known Activations