INDEX

Explanations

references to discussions or topics within a forum context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

visor

-0.18

 Volk

-0.15

xo

-0.14

icked

-0.14

Ð»Ð¸Ð·

-0.14

ificado

-0.14

DOMNode

-0.14

 VÃ¡c

-0.14

ware

-0.13

vik

-0.13

POSITIVE LOGITS

nic

0.16

 Carn

0.16

izzer

0.15

arness

0.14

bru

0.14

 incididunt

0.14

.docs

0.14

æ½

0.14

antly

0.13

unt

0.13

Activations Density 0.003%

references to discussions or topics within a forum context

No Comments

No Known Activations