INDEX

Explanations

instances of the verb "be" and its variations, focusing on states of existence or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 diligent

-0.18

--+

-0.15

uib

-0.15

 diligently

-0.15

roje

-0.14

Fol

-0.14

ashboard

-0.14

Ath

-0.14

ÑĥÐ²Ð°

-0.14

POSITIVE LOGITS

 cogn

0.24

 patient

0.23

 vocal

0.22

 forthcoming

0.22

 firm

0.21

 forth

0.20

 flexible

0.20

 circ

0.20

flex

0.19

 open

0.19

Activations Density 0.137%

instances of the verb "be" and its variations, focusing on states of existence or conditions

No Comments

No Known Activations