INDEX

Explanations

references to research teams and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

it

-0.15

ipes

-0.15

ateg

-0.15

aget

-0.14

iples

-0.14

ieber

-0.14

ulo

-0.14

 Ð¿ÑĢÐ¸Ð´ÐµÑĤÑģÑı

-0.14

bes

-0.14

bones

-0.14

POSITIVE LOGITS

 able

0.41

èĥ½å¤Ł

0.31

 Able

0.31

 ability

0.30

 Ability

0.28

Ability

0.25

 èĥ½

0.24

abled

0.23

ABLE

0.23

ability

0.22

Activations Density 0.094%

references to research teams and their activities

No Comments

No Known Activations