INDEX

Explanations

occurrences of the word "och" (which means "and" in Swedish) and its association with other words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

anny

-0.14

lement

-0.13

gz

-0.13

 permutations

-0.13

zar

-0.13

 Mobil

-0.13

à¥°

-0.13

ãĤ¿ãĥ¼

-0.13

 Latter

-0.13

eldon

-0.13

POSITIVE LOGITS

 famil

0.26

amilia

0.18

 family

0.18

ngth

0.18

ason

0.17

 Famil

0.17

 familia

0.17

ampoo

0.16

family

0.16

 famille

0.16

Activations Density 0.003%

occurrences of the word "och" (which means "and" in Swedish) and its association with other words

No Comments

No Known Activations