INDEX

Explanations

references to architectural projects and their details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

kw

-0.17

icut

-0.16

turnstile

-0.14

platz

-0.14

kh

-0.14

elper

-0.14

rome

-0.14

loth

-0.14

orting

-0.14

kr

-0.13

POSITIVE LOGITS

 Finland

0.55

 Finnish

0.53

 Helsinki

0.48

.fi

0.44

 Finn

0.42

Fin

0.38

FIN

0.35

elsinki

0.35

fin

0.35

Fin

0.34

Activations Density 0.081%

references to architectural projects and their details

No Comments

No Known Activations