INDEX

Explanations

references to data protection regulations and organizations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EDIA

-0.15

 Strike

-0.15

 strike

-0.15

ektor

-0.15

elah

-0.15

plorer

-0.14

eb

-0.14

æŃ

-0.14

ersh

-0.14

åĽŃ

-0.14

POSITIVE LOGITS

legg

0.16

arrow

0.15

iac

0.15

atak

0.14

rani

0.14

lamaz

0.14

aggio

0.14

ity

0.14

Ð¾Ð±Ð°

0.13

&amp

0.13

Activations Density 0.005%

references to data protection regulations and organizations

No Comments

No Known Activations