INDEX

Explanations

mathematical expressions and symbols related to functions and mappings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

hea

-0.16

kos

-0.15

opt

-0.15

wich

-0.15

tn

-0.14

 åŀ

-0.14

 tá»Ń

-0.14

ead

-0.14

 nostr

-0.14

 Lauderdale

-0.14

POSITIVE LOGITS

isma

0.16

 Animalia

0.15

rial

0.15

 NÄĽm

0.14

.getDrawable

0.14

shima

0.14

 Banks

0.14

lava

0.14

orial

0.13

Activations Density 0.019%

mathematical expressions and symbols related to functions and mappings

No Comments

No Known Activations