INDEX

Explanations

references to architectural projects and their attributes

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

icut

-0.15

kw

-0.15

kh

-0.15

loth

-0.15

CRET

-0.14

Squared

-0.14

 Pace

-0.14

 unlocks

-0.13

kh

-0.13

POSITIVE LOGITS

 Finland

0.49

 Finnish

0.48

 Helsinki

0.44

.fi

0.39

 Finn

0.33

 Mets

0.32

Fin

0.31

elsinki

0.31

 Nokia

0.31

fin

0.30

Activations Density 0.073%

references to architectural projects and their attributes

No Comments

No Known Activations