INDEX

Explanations

concepts related to operational efficiency and functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ollar

-0.14

kea

-0.14

anko

-0.14

VOL

-0.14

_GRAPH

-0.14

 ÑĩÐµÐ¼

-0.14

OUCH

-0.13

à¸ªà¸Ļ

-0.13

kowski

-0.13

abling

-0.13

POSITIVE LOGITS

0.16

0.15

<=$

0.15

streams

0.14

*&

0.14

umba

0.14

_slope

0.14

ÑĥÑĤ

0.14

blick

0.14

ons

0.14

Activations Density 0.558%

concepts related to operational efficiency and functionality

No Comments

No Known Activations