INDEX

Explanations

HTML or XML tags and elements within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

odu

-0.18

presso

-0.17

à¥įà¤¤à¤µ

-0.15

ANTE

-0.15

ÑģÑĤÐ²Ð¸Ðµ

-0.14

ìĶ

-0.14

 waivers

-0.14

appen

-0.14

ÑĢÐµÑĪ

-0.14

oui

-0.13

POSITIVE LOGITS

 covering

0.15

 resident

0.15

 Tweet

0.14

occ

0.14

assen

0.14

che

0.14

unt

0.14

Esp

0.13

 whether

0.13

velt

0.13

Activations Density 0.253%

HTML or XML tags and elements within a document

No Comments

No Known Activations