INDEX

Explanations

terms related to integration and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

iw

-0.16

icity

-0.15

 serialVersionUID

-0.15

eto

-0.15

iÅ¾

-0.15

asive

-0.15

ningar

-0.15

ëľ

-0.14

erne

-0.14

inheritDoc

-0.14

POSITIVE LOGITS

 into

0.23

emann

0.18

 Into

0.17

èĨľ

0.16

isty

0.16

Into

0.16

abelle

0.15

iste

0.15

 seamlessly

0.15

erdale

0.15

Activations Density 0.028%

terms related to integration and statistics

No Comments

No Known Activations