INDEX

Explanations

connections and relationships between concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ÐºÐ°Ð²

-0.16

 Herz

-0.15

uve

-0.15

usta

-0.15

ike

-0.14

zin

-0.14

.ItemStack

-0.14

.lucene

-0.13

:eq

-0.13

eron

-0.13

POSITIVE LOGITS

 Heat

0.15

 nhau

0.14

 secondary

0.14

argas

0.14

 Carp

0.14

utto

0.14

Heat

0.14

avenport

0.14

 neither

0.14

ado

0.14

Activations Density 0.093%

connections and relationships between concepts or entities

No Comments

No Known Activations