INDEX

Explanations

programming terms associated with data manipulation and API functions

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

Ð½ÐµÐ½

-0.15

bourg

-0.15

aktu

-0.15

ButtonModule

-0.15

onta

-0.14

peror

-0.14

ãĤ´ãĥª

-0.14

ceu

-0.14

 borderTop

-0.14

dak

-0.14

POSITIVE LOGITS

ag

0.16

iltr

0.15

0.14

 Prelude

0.14

ories

0.14

ÏĢÎµ

0.14

infinity

0.14

 Fabric

0.14

asil

0.14

Activations Density 0.251%

programming terms associated with data manipulation and API functions

No Comments

No Known Activations