INDEX

Explanations

references to specific biblical texts or verses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Kami

-0.15

.eng

-0.15

Ã²a

-0.15

èª

-0.15

ondo

-0.15

 rodin

-0.14

emble

-0.14

pollo

-0.14

istol

-0.14

umble

-0.14

POSITIVE LOGITS

 Judges

0.31

 Acts

0.30

Gal

0.30

 Luke

0.29

Col

0.29

Ps

0.29

 Numbers

0.28

Mic

0.28

Acts

0.28

 Matthew

0.27

Activations Density 0.154%

references to specific biblical texts or verses

No Comments

No Known Activations