INDEX

Explanations

references to authors or creators and their works in a meta-textual context

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

endir

-0.17

esian

-0.14

orne

-0.14

Ca

-0.14

roat

-0.13

eward

-0.13

metic

-0.13

ç¾©

-0.13

ata

-0.13

[--

-0.13

POSITIVE LOGITS

 itself

0.31

 themselves

0.22

 herself

0.21

 meta

0.19

 kendisi

0.19

èĩªèº«

0.18

meta

0.17

 selbst

0.17

 Himself

0.17

(meta

0.16

Activations Density 0.319%

references to authors or creators and their works in a meta-textual context

No Comments

No Known Activations