INDEX

Explanations

terms related to different fields of study, particularly in the sciences and medicine

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

esz

-0.16

ÑĢÐ¸Ð²

-0.15

åŃĿ

-0.15

Ã±as

-0.15

irling

-0.15

otime

-0.15

oved

-0.15

 tavs

-0.14

iot

-0.14

toFloat

-0.14

POSITIVE LOGITS

hci

0.18

vang

0.16

pig

0.15

hed

0.14

 peter

0.14

urum

0.14

 hitch

0.14

cade

0.14

acades

0.14

enzie

0.14

Activations Density 0.385%

terms related to different fields of study, particularly in the sciences and medicine

No Comments

No Known Activations