INDEX

Explanations

non-English characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ayah

-0.17

decorators

-0.15

disposing

-0.15

lazy

-0.15

kovÃ½

-0.15

Äįan

-0.15

ĵåĲį

-0.14

assa

-0.14

anker

-0.14

avou

-0.14

POSITIVE LOGITS

ãĤĩ

0.15

tek

0.15

ÐµÐ·Ð´

0.14

 erotische

0.14

 Exist

0.14

 duro

0.14

à¥Ģà¤²

0.13

Ã¼zel

0.13

è¼ī

0.13

ìĦł

0.13

Activations Density 0.004%

non-English characters or symbols

No Comments

No Known Activations