INDEX

Explanations

prepositions and articles indicating location

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

-0.16

lek

-0.16

ving

-0.15

ÙĬØ±Ø©

-0.15

oret

-0.15

les

-0.14

eket

-0.14

alm

-0.14

egie

-0.14

ESSAGES

-0.14

POSITIVE LOGITS

 sein

0.25

 detriment

0.22

 level

0.21

 moment

0.20

-dess

0.19

ÃŁerdem

0.18

 cours

0.16

 ëłĪë²¨

0.16

 seins

0.16

fur

0.15

Activations Density 0.006%

prepositions and articles indicating location

No Comments

No Known Activations