INDEX

Explanations

references to various styles and design elements

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

awy

-0.17

ĥn

-0.16

esser

-0.16

-0.15

wait

-0.14

orsi

-0.14

uyen

-0.14

é§

-0.14

ilde

-0.14

nap

-0.14

POSITIVE LOGITS

curity

0.16

gang

0.16

æħĭ

0.16

DNA

0.15

ovnÃŃ

0.15

uated

0.14

/style

0.14

HEET

0.14

osate

0.14

igi

0.14

Activations Density 0.037%

references to various styles and design elements

No Comments

No Known Activations