INDEX

Explanations

structured data and references to code or programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ertino

-0.20

Neutral

-0.16

 Neutral

-0.16

-neutral

-0.15

orra

-0.15

abble

-0.14

 neutral

-0.14

.AddListener

-0.14

omain

-0.14

iert

-0.14

POSITIVE LOGITS

Nun

0.15

Ð¾Ð»Ñİ

0.14

 Lester

0.14

 Ders

0.13

gomery

0.13

Arm

0.13

eson

0.13

 Ð¼ÐµÑĩ

0.13

rop

0.13

=forms

0.13

Activations Density 0.022%

structured data and references to code or programming constructs

No Comments

No Known Activations