INDEX

Explanations

terms and concepts related to definitions and interpretations in the context of biblical language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

olv

-0.15

quina

-0.15

ese

-0.15

åł±

-0.14

¶

-0.14

ves

-0.14

uler

-0.14

åľ

-0.14

izabeth

-0.14

icans

-0.14

POSITIVE LOGITS

 Greek

0.19

 Strong

0.17

Greek

0.16

Strong

0.16

 occurrences

0.15

ereo

0.15

 Transparency

0.15

ÐŁÐļ

0.15

cha

0.14

 transparency

0.14

Activations Density 0.023%

terms and concepts related to definitions and interpretations in the context of biblical language

No Comments

No Known Activations