INDEX

Explanations

topics that revolve around detailed explorations and discussions in academic and literary contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ares

-0.19

-0.16

olini

-0.15

aley

-0.15

áº©u

-0.14

/groups

-0.14

ÑģÑĤÐµÑĢ

-0.14

ibil

-0.14

.YES

-0.14

å®

-0.13

POSITIVE LOGITS

 subjects

0.20

 topics

0.19

Subjects

0.19

subjects

0.18

 Topics

0.16

how

0.16

 Subjects

0.15

topic

0.15

/about

0.15

topics

0.14

Activations Density 0.142%

topics that revolve around detailed explorations and discussions in academic and literary contexts

No Comments

No Known Activations