INDEX

Explanations

historical references to notable figures and events in entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

heimer

-0.16

 predecess

-0.14

ATCH

-0.14

å²Ĺ

-0.13

é¾Ħ

-0.13

 deliberately

-0.13

azzi

-0.13

hea

-0.13

ÑįÑĦ

-0.13

ACK

-0.12

POSITIVE LOGITS

ovel

0.15

/sweetalert

0.14

enas

0.14

preter

0.14

Ø§ÙĩÛĮ

0.13

Nonnull

0.13

arness

0.13

mÃ®

0.13

à¹īà¸²à¸ª

0.13

VertexBuffer

0.13

Activations Density 1.056%

historical references to notable figures and events in entertainment

No Comments

No Known Activations