INDEX

Explanations

occurrences of the term "High" indicating notable or elevated concepts or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ìģc

-0.16

ody

-0.15

Ìĥ

-0.14

nut

-0.14

strup

-0.14

oma

-0.14

ed

-0.14

oman

-0.14

 ÏĥÏħÎ½

-0.14

indo

-0.14

POSITIVE LOGITS

 Noon

0.23

school

0.22

noon

0.21

 school

0.20

ways

0.20

lander

0.20

 School

0.19

berger

0.19

gate

0.19

lands

0.18

Activations Density 0.039%

occurrences of the term "High" indicating notable or elevated concepts or themes

No Comments

No Known Activations