INDEX

Explanations

phrases related to software licensing and terms of use

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ÛĮØ§Øª

-0.15

Å¡ov

-0.15

¦¬

-0.14

_misc

-0.14

ubre

-0.13

pac

-0.13

WXYZ

-0.13

awns

-0.13

igli

-0.13

 Furniture

-0.13

POSITIVE LOGITS

Ð¸Ð½Ð¾Ðº

0.15

anine

0.14

ç«

0.14

oon

0.14

 Reed

0.14

arend

0.13

ÑĢÐ¾Ð¶

0.13

ãĥĮ

0.13

SD

0.13

ves

0.13

Activations Density 0.002%

phrases related to software licensing and terms of use

No Comments

No Known Activations