INDEX

Explanations

references to religious institutions and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Ã¶y

-0.18

etros

-0.15

oload

-0.15

reb

-0.14

ileo

-0.14

 Minerals

-0.14

orts

-0.14

ÃŃl

-0.14

 Walt

-0.13

 Robbie

-0.13

POSITIVE LOGITS

 Carm

0.35

 Franc

0.33

fri

0.33

 Domin

0.27

 Sisters

0.27

 Dominican

0.27

Fri

0.26

 Sales

0.25

Cap

0.25

Activations Density 0.041%

references to religious institutions and figures

No Comments

No Known Activations