INDEX

Explanations

references to various associations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ORIZONTAL

-0.16

NAMESPACE

-0.15

 acomp

-0.14

nell

-0.14

utin

-0.13

èī²

-0.13

uess

-0.13

ÏĢÎ»

-0.13

/frame

-0.13

 inher

-0.13

POSITIVE LOGITS

ENCHMARK

0.16

iliz

0.14

ebp

0.14

ultip

0.13

ê¸ī

0.13

à¸ªà¸Ķ

0.13

groupBox

0.13

Activations Density 0.025%

references to various associations and organizations

No Comments

No Known Activations