INDEX

Explanations

details related to educational or instructional sessions

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

 rallies

-0.16

èª

-0.15

ibox

-0.15

apus

-0.14

uis

-0.14

ensch

-0.14

vero

-0.14

Å¡ak

-0.14

 overst

-0.14

ula

-0.13

POSITIVE LOGITS

 behalf

0.35

 basis

0.24

 occasion

0.24

 grounds

0.23

basis

0.22

occasion

0.21

 occasions

0.20

_basis

0.18

ze

0.17

 scales

0.15

Activations Density 0.632%

details related to educational or instructional sessions

No Comments

No Known Activations