INDEX

Explanations

bilateral terms and concepts related to energy and service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

igh

-0.16

shaw

-0.15

ÑĦÐ¸Ðº

-0.15

Publish

-0.15

ublik

-0.15

utes

-0.14

Bed

-0.14

IGH

-0.14

hest

-0.14

ib

-0.14

POSITIVE LOGITS

ãĤ¦ãĤ©

0.17

ãĥ¯

0.17

_W

0.16

pha

0.16

ldre

0.16

essler

0.16

_O

0.15

 Oliveira

0.15

ãĤ¨ãĥ«

0.15

ï¼¯

0.15

Activations Density 0.046%

bilateral terms and concepts related to energy and service

No Comments

No Known Activations